Want to use your own AI? Check out our new MCP-only product →
Want to use your own AI? Check out our new MCP-only product →
If you've ever asked Perplexity a question like "should I rebalance my retirement accounts?" or "am I overexposed to tech?" — you already know what comes back. A neat-sounding paragraph stitching together search results and general advice. Maybe a 60/40 allocation example pulled from a recent article. Definitely no actual numbers from your accounts.
That's because Perplexity — like Claude, ChatGPT, Mistral, and every other LLM-based assistant — doesn't know your accounts. Its search-augmented architecture pulls in web context (current market commentary, recent news, public knowledge) but stops there. It has no idea you hold $14,000 in TSLA, no idea your 401(k) is a 2055 target-date fund at 87 basis points, no idea you have $3,200 of cash drag in your taxable brokerage.
Truthifi closes that gap. Once you connect Truthifi to Perplexity, every thread can pull live, read-only data from your real accounts — combined with Perplexity's web-search layer in the same response. This is where Perplexity's design actually shines: search-augmented answers are good because they ground the model in current public context. With Truthifi added, they're also grounded in your private context.
This guide covers what changes when Perplexity can see your real accounts, what makes a financial MCP connector trustworthy, and a sample of questions that suddenly become answerable — including several that benefit specifically from Perplexity's signature citation-rich answer style.
Why AI gives generic financial answers
Search-augmented or not, every AI assistant runs into the same wall on personal-finance questions: it has no idea who you are or what you own. Perplexity can pull current market commentary, cite recent fund research, and explain the difference between a Roth and a traditional IRA — all valuable. But none of that requires it to know that you specifically hold a 2055 target-date fund at 87 basis points.
The moment you ask a question that depends on your specific situation — "is my asset allocation appropriate for my risk tolerance?" — the model is forced to invent a hypothetical you. It might assume you're 35, earn $120k, have $50k in retirement accounts and $10k in cash. Maybe one of those numbers happens to be right. Most won't.
This is more than an inconvenience. It's the structural reason "talk to AI about your finances" has been disappointing for everyone who's tried it seriously. The advice can only be as specific as the model's understanding of your situation. With no understanding, the advice has no choice but to be generic.
There's a second-order problem too: generic advice that sounds confident is worse than no advice at all. A reader who asks "should I be selling my tech holdings right now?" and gets back a thoughtful-sounding paragraph about not timing the market is being told something that may or may not apply to them. If their tech allocation is already 80% of their portfolio, the answer should be different than if it's 5%. The agent can't know which case they're in. It picks a plausible answer for a typical reader and serves that — and a non-typical reader gets advice tuned for someone else.
Perplexity in particular has a unique vulnerability to this failure mode. The agent's selling point is high-quality, citation-backed answers grounded in current information. When you ask Perplexity about your portfolio without Truthifi, it dutifully cites sources for the general advice it gives — which can paradoxically make the generic answer feel more trustworthy than it should. A confident citation to a Vanguard target-date methodology paper, applied to a hypothetical you who isn't you, is harder to spot as misleading than a vague "consult a financial advisor" deflection. Citation quality without personal grounding is a particular trap for the search-augmented architecture.
Pasting screenshots or CSV exports into Perplexity helps for one thread, then becomes stale the moment a position trades. And every paste is a manual chore that you'll do twice and abandon by the third week.
Perplexity is a particularly interesting case because its search-augmented architecture is uniquely capable of synthesizing public knowledge with personal data — if the personal data is there. Without it, the search-augmentation only delivers half the value. The whole reason to use Perplexity over a chat-style assistant is the citation-rich, current-context grounded answers. Adding personal data via Truthifi unlocks the other half: citation-rich answers grounded in your current context.
The fix is structural, not procedural: give Perplexity a live connection to your actual accounts. Once it's there, you don't need to remember to paste anything. Perplexity calls Truthifi when needed, gets fresh data, combines it with its web-search layer, answers — and the answer cites both Truthifi and web sources distinctly so you can see which parts of the answer came from where.
The two ways to give Perplexity your financial data
Two paths exist. One is fragile and risky. The other is purpose-built.
The DIY path: paste, repeat, hope. You log into your brokerage, export a CSV, paste it into Perplexity. Or you describe your portfolio in plain English and ask Perplexity to assume those numbers. Both work — kind of — and both have problems. CSVs decay the moment any position trades. Verbal portfolio descriptions are slow to type and error-prone. And neither approach handles cross-account questions: Fidelity, Schwab, and Vanguard describe holdings differently, so even if you paste all three, Perplexity has to do the cross-referencing in its head.
There's a deeper issue with the DIY approach that doesn't show up until you've been doing it for a few weeks. Your data and your reasoning drift apart. You ask a question on Tuesday based on Monday's CSV; Perplexity tells you something. The position changed Monday afternoon. The advice you got on Tuesday is now wrong, but you act on it anyway because you don't realize. This isn't Perplexity's fault — it's working with what you gave it. But the failure mode is silent.
For Perplexity specifically, the DIY problem has a sharper edge. Perplexity's value-add is the freshness and traceability of its answers. When you paste an old CSV, Perplexity has no way to mark its own answer as "data from Monday's snapshot, public market context as of right now." You get a single-citation answer that mixes stale personal data with fresh public data, presented with the same confidence. Citation hygiene is what Perplexity does well — and the DIY path defeats it.
The purpose-built path: Truthifi's read-only MCP. Truthifi connects to your real financial institutions through industry-standard aggregation, normalizes the data into a consistent schema, and exposes it to Perplexity via the Model Context Protocol. Your brokerage credentials stay at your brokerage. Perplexity gets a scoped OAuth token that can read facts and nothing else. When data changes on your accounts, Truthifi reflects it the next time Perplexity queries.
Perplexity handles MCP natively as of March 2026 — the custom-connector flow in account settings is the official entry point. You don't need to write glue code or run a local proxy. Add Truthifi from the Connectors menu, complete OAuth, done.
The architectural difference matters. With CSV pastes, your data lives in conversation history and ages there. With a hypothetical-portfolio description, your data is wrong from the start. With Truthifi's MCP, the data lives at Truthifi (already a wealth-monitoring service designed to hold it), and Perplexity queries it on demand. Each component does the thing it's good at: Truthifi does data aggregation and normalization; Perplexity does search-augmented reasoning. Neither is doing work it shouldn't.
There's also a Perplexity-specific architectural payoff: Perplexity's search layer pulls fresh public sources on demand, and Truthifi's MCP layer pulls fresh portfolio data on demand. The two layers have similar freshness profiles, similar citation patterns, and integrate naturally in Perplexity's response format. The combined answer reads as one coherent citation-backed response rather than as two pasted-together chunks.
What makes a financial MCP connector trustworthy
MCP servers vary widely in what they expose and how they handle data. For a financial connector — the kind that will sit between Perplexity and your real account balances — four properties deserve particular scrutiny.
Read-only by design. Truthifi's MCP server cannot initiate transactions, modify accounts, or move money. There is no write capability anywhere in the connector. This isn't just a permissions configuration — there's no API path through Truthifi to a transactional endpoint at your brokerage. Even if your Perplexity OAuth token were leaked, the worst an attacker could do is read what you can already read.
The asymmetry is structural. Truthifi's API surface only exposes read tools. Adding write paths would require a different product, not a different scope on the same one.
For Perplexity users specifically, this matters because Perplexity is increasingly used for action-planning ("research X then summarize Y"). Even if a Perplexity workflow generated a confident "you should sell" recommendation, it cannot execute. The action gap is enforced at the connector level, not at the agent level — important for an agent whose research-and-recommend posture might otherwise blur into research-and-execute over time.
Scoped OAuth, not credentials. When Perplexity connects, Truthifi issues a token that's specifically scoped to read-only Truthifi tools. Your brokerage username and password are never on Perplexity's servers, never on Truthifi's servers — they're at your brokerage where they belong. The token can be revoked from either side at any time.
This matters more for hosted platforms like Perplexity than it does for local tools, because Perplexity stores connector tokens server-side. The scoped-OAuth model means the worst-case data exposure if Perplexity were ever breached is the read-only Truthifi token, which is itself revocable.
Transparent audit trail. A trustworthy connector logs every tool call with timestamps and the requesting connector. Truthifi maintains a per-connector audit log on the Truthifi side; Perplexity maintains its own conversation history. Two independent audit trails is the level of due diligence you'd want from any production-grade financial integration.
This matters because if something goes wrong or anomalous later, you can cross-reference the two logs. The Truthifi-side log shows you what was queried; the Perplexity-side log shows you what conversation triggered the query. Together they answer "what happened, when, and why."
No data exfiltration. Perplexity should be the only consumer of your Truthifi token. The connector doesn't ship your data anywhere else, doesn't train on it, doesn't expose it to other Truthifi customers. Your data is yours. Truthifi normalizes it for query, holds it just long enough to answer, and discards working copies.
Perplexity's privacy policy specifically addresses connector data — connector responses are used to answer your specific query and are not retained for training. Combined with Truthifi's read-only design, you get a meaningfully strong privacy posture for a hosted AI service. Worth highlighting: Perplexity's citation-backed answer format means connector data appearing in responses is explicitly attributed, not silently incorporated. You can see exactly which numbers in an answer came from Truthifi versus from web sources.
What to ask once your portfolio is connected
Once Truthifi is registered with Perplexity, the questions you can productively ask change in shape. Here's a sample, organized by what they reveal — and what a useful answer actually looks like.
Allocation reality with web context. "Compare my current allocation across all accounts to a 70/25/5 stocks/bonds/cash target. Pull current market commentary on whether 70/25/5 is appropriate given today's rate environment, and tell me what I'd need to rebalance."
A useful response: "Your current allocation is 78% stocks, 17% bonds, 5% cash [Truthifi]. To hit 70/25/5, you'd need to sell about $42,000 of stock holdings and buy $42,000 of bonds. The most tax-efficient way to do this is in your tax-advantaged accounts — your 401(k) at Fidelity has $58,000 in equities; rebalancing $42,000 of that to bond funds incurs no tax. Note: market commentary [3 web citations] suggests a potential rate cut cycle in the next 6 months, which would generally favor longer-duration bond exposure. If you're moving to bonds anyway, intermediate-to-longer duration funds may be worth weighting toward."
Real numbers, real recommendations, account-specific guidance, plus public-context augmentation that's traceable to specific cited sources.
Concentration risk. "What's my single largest position as a percentage of total portfolio?"
A useful response: "Your largest position is GOOG, holding $87,200 across your taxable Schwab and IRA accounts — 12.4% of portfolio [Truthifi]. Top five (GOOG, AAPL, VTI, VOO, MSFT) total 38.6% of portfolio. Note: GOOG and AAPL are both in tech, so your effective tech concentration through these two is 14.8% of portfolio."
Web-augmented fee analysis. "Pull the expense ratios for every mutual fund I hold and rank them. Cross-check against current Vanguard equivalents — flag anything where I'd save more than 30 bps by switching."
This is where Perplexity's search-augmented design genuinely shines. It pulls expense ratios from your actual holdings via Truthifi, then queries the public Vanguard fund database for equivalents, and produces a comparison grounded in both layers — with citations to the public Vanguard pages so you can verify the equivalent funds yourself.
A useful response: "Across your 11 mutual fund holdings, the median expense ratio is 22 bps [Truthifi]. Three funds significantly exceed Vanguard equivalents:
AGTHX (Capital Group Growth Fund of America) at 64 bps in your traditional IRA. Closest Vanguard equivalent: VTSAX at 4 bps [Vanguard.com]. Annual savings on $43,000 position: ~$258.
OAKMX (Oakmark Fund) at 81 bps in your taxable Fidelity. Closest equivalent: VOO at 3 bps [Vanguard.com]. Annual savings on $28,000 position: ~$218.
ABALX (American Funds Balanced) at 56 bps in your 401(k) at Vanguard. Closest equivalent: VBIAX at 8 bps [Vanguard.com]. Annual savings on $51,000 position: ~$245."
Web citations on the comparison side, Truthifi citations on the personal side. Reader can verify both.
Tax-loss harvesting candidates. "Which positions in my taxable accounts are at a loss right now? Show me cost basis and current value, plus the wash-sale window for each."
A useful response: "You have 3 positions in taxable accounts at a loss [Truthifi]: BABA at -$2,140 (cost basis $4,800, current $2,660), PYPL at -$890, and DIS at -$340. Wash-sale considerations: the BABA loss can be harvested cleanly (no replacement purchases in past 30 days). PYPL had a small purchase 12 days ago — harvesting now would partially disallow the loss. Note: current IRS guidance on wash-sale rules [Treasury cite] confirms the standard 30-day window applies; no recent rulings affect this."
Cross-account totals. "Sum my retirement accounts across all custodians. Break down by account type — Roth, traditional, 401(k), HSA."
Cash drag. "How much cash am I sitting on across all accounts? At current Treasury yields (pull these from the latest auction), what's the opportunity cost?"
Web-augmented again — Perplexity pulls current Treasury yields from public sources, then computes the opportunity cost on your actual cash balance.
Dividend timing. "What dividends am I expecting in the next 30 days, and from which positions?"
Recent-context decisions. "Given the latest [Federal Reserve / earnings season / market move], what positions in my portfolio are most exposed?"
This kind of question is where Perplexity is meaningfully different from any other AI agent. It pulls fresh news context from the web alongside your portfolio, and frames the answer in terms of your exposure, not generic exposure. Useful response format: "The Fed's recent guidance shift toward [specific policy stance] [Reuters citation] particularly affects rate-sensitive positions. In your portfolio [Truthifi], your three largest interest-rate-sensitive holdings are [REIT or bond fund A] at $X, [REIT or bond fund B] at $Y, and [position C] at $Z. The combined exposure is W% of your portfolio."
Comparison-shopping with public data. "I'm thinking about switching from my current target-date fund. Pull current expense ratios and historical performance from public sources for similar 2055 funds. Compare to what I currently own."
Perplexity pulls public fund data and combines with your current holding details from Truthifi. The output is a citation-backed comparison table where you can see exactly which performance numbers came from which fund providers' public data.
The pattern across all of these: Perplexity doesn't need you to specify which accounts to look at, where the data lives, or what format to use. Truthifi has already normalized everything. Perplexity queries, reasons, augments with web search where relevant, and answers — with explicit citations distinguishing your private portfolio data from public web data.
How to connect Truthifi to Perplexity
The setup takes about two minutes. Available on Pro, Max, and Enterprise plans.
The full step-by-step is here: How to Connect Your Portfolio to Perplexity via Truthifi MCP.
Short version: Account Settings → Connectors → "+ Custom connector" → Remote → fill in Name "Truthifi", URL https://api.truthifi.com/mcp, Description, OAuth 2.0 auth, leave Transport at default → check risk acknowledgement → Add → click Truthifi card to start OAuth → grant scope → done.
Toggle Truthifi on per thread when you want it active. Web-augmented answers and Truthifi-grounded answers can coexist in the same response.
What Perplexity can and can't do with your data
Perplexity can:
Read your account balances, holdings, cost basis, and transaction history.
Read your Truthifi Score and Truthifi findings.
Compute, analyze, summarize, and answer questions across any combination.
Combine portfolio facts with web-search context (current market data, news, fund-specific information).
Cite Truthifi as a source distinct from web sources, so you can see which parts of an answer came from your accounts vs. from public web.
Use connector data inside Perplexity Spaces for ongoing research workflows.
Perplexity cannot:
Initiate trades, transfers, or any money movement.
Modify your Truthifi or brokerage account settings.
Add, remove, or reauthorize financial-institution connections (you do that in Truthifi).
Access your bank or brokerage credentials. They never leave your bank or brokerage.
Persist your data outside of Perplexity's standard conversation retention.
Make decisions for you. Perplexity is good at surfacing facts, doing math, and explaining trade-offs. It is not good at "should I sell" — that's still your call.
The asymmetry is intentional: read-everything, write-nothing. The right shape for an AI assistant connected to your accounts.
This is what AI agents were built for
The original promise of AI agents was assistants that could actually help, not just generate plausible-sounding paragraphs. For most use cases — drafting an email, summarizing a meeting, debugging code — that promise has been delivered. For personal finance, it's been mostly stuck because the agent didn't know your real situation.
Perplexity plus Truthifi closes that gap specifically for users who want an answer engine — one that takes a question, searches whatever's relevant, grounds in your actual data, and returns a citation-backed response. The thing that distinguishes Perplexity from chat-style assistants like Claude or ChatGPT is the search-and-cite design. With Truthifi added, "and your portfolio" becomes a grounded source the same way "and the web" is.
This is also the configuration that holds up best as more financial services expose MCP endpoints — something a number of major institutions are starting to do. As tax software exposes returns, as estate-planning tools expose beneficiary status, as insurance carriers expose policy details, your Perplexity becomes the single answer engine that knows everything you've authorized it to know. Same threading pattern, same citation model, same trust posture.
The longer-term thing worth noting: web context plus your real data is structurally different from either alone. Generic financial advice based on web context is what every LLM does poorly. Account-specific advice without market context is what spreadsheet aggregators do badly. The combination — Perplexity's job — is genuinely useful when both layers are present. Truthifi makes the second layer present.
Perplexity Spaces deserves separate mention. Spaces let you set up persistent research collections that pull from your connected sources every time you open them. With Truthifi connected, you can create a "weekly portfolio review" Space that always greets you with current allocation, top concentrations, recent transactions, and any flagged Truthifi findings — augmented by current market commentary from Perplexity's web layer. That kind of standing dashboard is much more powerful with personal data wired in.
If you've ever asked Perplexity a question like "should I rebalance my retirement accounts?" or "am I overexposed to tech?" — you already know what comes back. A neat-sounding paragraph stitching together search results and general advice. Maybe a 60/40 allocation example pulled from a recent article. Definitely no actual numbers from your accounts.
That's because Perplexity — like Claude, ChatGPT, Mistral, and every other LLM-based assistant — doesn't know your accounts. Its search-augmented architecture pulls in web context (current market commentary, recent news, public knowledge) but stops there. It has no idea you hold $14,000 in TSLA, no idea your 401(k) is a 2055 target-date fund at 87 basis points, no idea you have $3,200 of cash drag in your taxable brokerage.
Truthifi closes that gap. Once you connect Truthifi to Perplexity, every thread can pull live, read-only data from your real accounts — combined with Perplexity's web-search layer in the same response. This is where Perplexity's design actually shines: search-augmented answers are good because they ground the model in current public context. With Truthifi added, they're also grounded in your private context.
This guide covers what changes when Perplexity can see your real accounts, what makes a financial MCP connector trustworthy, and a sample of questions that suddenly become answerable — including several that benefit specifically from Perplexity's signature citation-rich answer style.
Why AI gives generic financial answers
Search-augmented or not, every AI assistant runs into the same wall on personal-finance questions: it has no idea who you are or what you own. Perplexity can pull current market commentary, cite recent fund research, and explain the difference between a Roth and a traditional IRA — all valuable. But none of that requires it to know that you specifically hold a 2055 target-date fund at 87 basis points.
The moment you ask a question that depends on your specific situation — "is my asset allocation appropriate for my risk tolerance?" — the model is forced to invent a hypothetical you. It might assume you're 35, earn $120k, have $50k in retirement accounts and $10k in cash. Maybe one of those numbers happens to be right. Most won't.
This is more than an inconvenience. It's the structural reason "talk to AI about your finances" has been disappointing for everyone who's tried it seriously. The advice can only be as specific as the model's understanding of your situation. With no understanding, the advice has no choice but to be generic.
There's a second-order problem too: generic advice that sounds confident is worse than no advice at all. A reader who asks "should I be selling my tech holdings right now?" and gets back a thoughtful-sounding paragraph about not timing the market is being told something that may or may not apply to them. If their tech allocation is already 80% of their portfolio, the answer should be different than if it's 5%. The agent can't know which case they're in. It picks a plausible answer for a typical reader and serves that — and a non-typical reader gets advice tuned for someone else.
Perplexity in particular has a unique vulnerability to this failure mode. The agent's selling point is high-quality, citation-backed answers grounded in current information. When you ask Perplexity about your portfolio without Truthifi, it dutifully cites sources for the general advice it gives — which can paradoxically make the generic answer feel more trustworthy than it should. A confident citation to a Vanguard target-date methodology paper, applied to a hypothetical you who isn't you, is harder to spot as misleading than a vague "consult a financial advisor" deflection. Citation quality without personal grounding is a particular trap for the search-augmented architecture.
Pasting screenshots or CSV exports into Perplexity helps for one thread, then becomes stale the moment a position trades. And every paste is a manual chore that you'll do twice and abandon by the third week.
Perplexity is a particularly interesting case because its search-augmented architecture is uniquely capable of synthesizing public knowledge with personal data — if the personal data is there. Without it, the search-augmentation only delivers half the value. The whole reason to use Perplexity over a chat-style assistant is the citation-rich, current-context grounded answers. Adding personal data via Truthifi unlocks the other half: citation-rich answers grounded in your current context.
The fix is structural, not procedural: give Perplexity a live connection to your actual accounts. Once it's there, you don't need to remember to paste anything. Perplexity calls Truthifi when needed, gets fresh data, combines it with its web-search layer, answers — and the answer cites both Truthifi and web sources distinctly so you can see which parts of the answer came from where.
The two ways to give Perplexity your financial data
Two paths exist. One is fragile and risky. The other is purpose-built.
The DIY path: paste, repeat, hope. You log into your brokerage, export a CSV, paste it into Perplexity. Or you describe your portfolio in plain English and ask Perplexity to assume those numbers. Both work — kind of — and both have problems. CSVs decay the moment any position trades. Verbal portfolio descriptions are slow to type and error-prone. And neither approach handles cross-account questions: Fidelity, Schwab, and Vanguard describe holdings differently, so even if you paste all three, Perplexity has to do the cross-referencing in its head.
There's a deeper issue with the DIY approach that doesn't show up until you've been doing it for a few weeks. Your data and your reasoning drift apart. You ask a question on Tuesday based on Monday's CSV; Perplexity tells you something. The position changed Monday afternoon. The advice you got on Tuesday is now wrong, but you act on it anyway because you don't realize. This isn't Perplexity's fault — it's working with what you gave it. But the failure mode is silent.
For Perplexity specifically, the DIY problem has a sharper edge. Perplexity's value-add is the freshness and traceability of its answers. When you paste an old CSV, Perplexity has no way to mark its own answer as "data from Monday's snapshot, public market context as of right now." You get a single-citation answer that mixes stale personal data with fresh public data, presented with the same confidence. Citation hygiene is what Perplexity does well — and the DIY path defeats it.
The purpose-built path: Truthifi's read-only MCP. Truthifi connects to your real financial institutions through industry-standard aggregation, normalizes the data into a consistent schema, and exposes it to Perplexity via the Model Context Protocol. Your brokerage credentials stay at your brokerage. Perplexity gets a scoped OAuth token that can read facts and nothing else. When data changes on your accounts, Truthifi reflects it the next time Perplexity queries.
Perplexity handles MCP natively as of March 2026 — the custom-connector flow in account settings is the official entry point. You don't need to write glue code or run a local proxy. Add Truthifi from the Connectors menu, complete OAuth, done.
The architectural difference matters. With CSV pastes, your data lives in conversation history and ages there. With a hypothetical-portfolio description, your data is wrong from the start. With Truthifi's MCP, the data lives at Truthifi (already a wealth-monitoring service designed to hold it), and Perplexity queries it on demand. Each component does the thing it's good at: Truthifi does data aggregation and normalization; Perplexity does search-augmented reasoning. Neither is doing work it shouldn't.
There's also a Perplexity-specific architectural payoff: Perplexity's search layer pulls fresh public sources on demand, and Truthifi's MCP layer pulls fresh portfolio data on demand. The two layers have similar freshness profiles, similar citation patterns, and integrate naturally in Perplexity's response format. The combined answer reads as one coherent citation-backed response rather than as two pasted-together chunks.
What makes a financial MCP connector trustworthy
MCP servers vary widely in what they expose and how they handle data. For a financial connector — the kind that will sit between Perplexity and your real account balances — four properties deserve particular scrutiny.
Read-only by design. Truthifi's MCP server cannot initiate transactions, modify accounts, or move money. There is no write capability anywhere in the connector. This isn't just a permissions configuration — there's no API path through Truthifi to a transactional endpoint at your brokerage. Even if your Perplexity OAuth token were leaked, the worst an attacker could do is read what you can already read.
The asymmetry is structural. Truthifi's API surface only exposes read tools. Adding write paths would require a different product, not a different scope on the same one.
For Perplexity users specifically, this matters because Perplexity is increasingly used for action-planning ("research X then summarize Y"). Even if a Perplexity workflow generated a confident "you should sell" recommendation, it cannot execute. The action gap is enforced at the connector level, not at the agent level — important for an agent whose research-and-recommend posture might otherwise blur into research-and-execute over time.
Scoped OAuth, not credentials. When Perplexity connects, Truthifi issues a token that's specifically scoped to read-only Truthifi tools. Your brokerage username and password are never on Perplexity's servers, never on Truthifi's servers — they're at your brokerage where they belong. The token can be revoked from either side at any time.
This matters more for hosted platforms like Perplexity than it does for local tools, because Perplexity stores connector tokens server-side. The scoped-OAuth model means the worst-case data exposure if Perplexity were ever breached is the read-only Truthifi token, which is itself revocable.
Transparent audit trail. A trustworthy connector logs every tool call with timestamps and the requesting connector. Truthifi maintains a per-connector audit log on the Truthifi side; Perplexity maintains its own conversation history. Two independent audit trails is the level of due diligence you'd want from any production-grade financial integration.
This matters because if something goes wrong or anomalous later, you can cross-reference the two logs. The Truthifi-side log shows you what was queried; the Perplexity-side log shows you what conversation triggered the query. Together they answer "what happened, when, and why."
No data exfiltration. Perplexity should be the only consumer of your Truthifi token. The connector doesn't ship your data anywhere else, doesn't train on it, doesn't expose it to other Truthifi customers. Your data is yours. Truthifi normalizes it for query, holds it just long enough to answer, and discards working copies.
Perplexity's privacy policy specifically addresses connector data — connector responses are used to answer your specific query and are not retained for training. Combined with Truthifi's read-only design, you get a meaningfully strong privacy posture for a hosted AI service. Worth highlighting: Perplexity's citation-backed answer format means connector data appearing in responses is explicitly attributed, not silently incorporated. You can see exactly which numbers in an answer came from Truthifi versus from web sources.
What to ask once your portfolio is connected
Once Truthifi is registered with Perplexity, the questions you can productively ask change in shape. Here's a sample, organized by what they reveal — and what a useful answer actually looks like.
Allocation reality with web context. "Compare my current allocation across all accounts to a 70/25/5 stocks/bonds/cash target. Pull current market commentary on whether 70/25/5 is appropriate given today's rate environment, and tell me what I'd need to rebalance."
A useful response: "Your current allocation is 78% stocks, 17% bonds, 5% cash [Truthifi]. To hit 70/25/5, you'd need to sell about $42,000 of stock holdings and buy $42,000 of bonds. The most tax-efficient way to do this is in your tax-advantaged accounts — your 401(k) at Fidelity has $58,000 in equities; rebalancing $42,000 of that to bond funds incurs no tax. Note: market commentary [3 web citations] suggests a potential rate cut cycle in the next 6 months, which would generally favor longer-duration bond exposure. If you're moving to bonds anyway, intermediate-to-longer duration funds may be worth weighting toward."
Real numbers, real recommendations, account-specific guidance, plus public-context augmentation that's traceable to specific cited sources.
Concentration risk. "What's my single largest position as a percentage of total portfolio?"
A useful response: "Your largest position is GOOG, holding $87,200 across your taxable Schwab and IRA accounts — 12.4% of portfolio [Truthifi]. Top five (GOOG, AAPL, VTI, VOO, MSFT) total 38.6% of portfolio. Note: GOOG and AAPL are both in tech, so your effective tech concentration through these two is 14.8% of portfolio."
Web-augmented fee analysis. "Pull the expense ratios for every mutual fund I hold and rank them. Cross-check against current Vanguard equivalents — flag anything where I'd save more than 30 bps by switching."
This is where Perplexity's search-augmented design genuinely shines. It pulls expense ratios from your actual holdings via Truthifi, then queries the public Vanguard fund database for equivalents, and produces a comparison grounded in both layers — with citations to the public Vanguard pages so you can verify the equivalent funds yourself.
A useful response: "Across your 11 mutual fund holdings, the median expense ratio is 22 bps [Truthifi]. Three funds significantly exceed Vanguard equivalents:
AGTHX (Capital Group Growth Fund of America) at 64 bps in your traditional IRA. Closest Vanguard equivalent: VTSAX at 4 bps [Vanguard.com]. Annual savings on $43,000 position: ~$258.
OAKMX (Oakmark Fund) at 81 bps in your taxable Fidelity. Closest equivalent: VOO at 3 bps [Vanguard.com]. Annual savings on $28,000 position: ~$218.
ABALX (American Funds Balanced) at 56 bps in your 401(k) at Vanguard. Closest equivalent: VBIAX at 8 bps [Vanguard.com]. Annual savings on $51,000 position: ~$245."
Web citations on the comparison side, Truthifi citations on the personal side. Reader can verify both.
Tax-loss harvesting candidates. "Which positions in my taxable accounts are at a loss right now? Show me cost basis and current value, plus the wash-sale window for each."
A useful response: "You have 3 positions in taxable accounts at a loss [Truthifi]: BABA at -$2,140 (cost basis $4,800, current $2,660), PYPL at -$890, and DIS at -$340. Wash-sale considerations: the BABA loss can be harvested cleanly (no replacement purchases in past 30 days). PYPL had a small purchase 12 days ago — harvesting now would partially disallow the loss. Note: current IRS guidance on wash-sale rules [Treasury cite] confirms the standard 30-day window applies; no recent rulings affect this."
Cross-account totals. "Sum my retirement accounts across all custodians. Break down by account type — Roth, traditional, 401(k), HSA."
Cash drag. "How much cash am I sitting on across all accounts? At current Treasury yields (pull these from the latest auction), what's the opportunity cost?"
Web-augmented again — Perplexity pulls current Treasury yields from public sources, then computes the opportunity cost on your actual cash balance.
Dividend timing. "What dividends am I expecting in the next 30 days, and from which positions?"
Recent-context decisions. "Given the latest [Federal Reserve / earnings season / market move], what positions in my portfolio are most exposed?"
This kind of question is where Perplexity is meaningfully different from any other AI agent. It pulls fresh news context from the web alongside your portfolio, and frames the answer in terms of your exposure, not generic exposure. Useful response format: "The Fed's recent guidance shift toward [specific policy stance] [Reuters citation] particularly affects rate-sensitive positions. In your portfolio [Truthifi], your three largest interest-rate-sensitive holdings are [REIT or bond fund A] at $X, [REIT or bond fund B] at $Y, and [position C] at $Z. The combined exposure is W% of your portfolio."
Comparison-shopping with public data. "I'm thinking about switching from my current target-date fund. Pull current expense ratios and historical performance from public sources for similar 2055 funds. Compare to what I currently own."
Perplexity pulls public fund data and combines with your current holding details from Truthifi. The output is a citation-backed comparison table where you can see exactly which performance numbers came from which fund providers' public data.
The pattern across all of these: Perplexity doesn't need you to specify which accounts to look at, where the data lives, or what format to use. Truthifi has already normalized everything. Perplexity queries, reasons, augments with web search where relevant, and answers — with explicit citations distinguishing your private portfolio data from public web data.
How to connect Truthifi to Perplexity
The setup takes about two minutes. Available on Pro, Max, and Enterprise plans.
The full step-by-step is here: How to Connect Your Portfolio to Perplexity via Truthifi MCP.
Short version: Account Settings → Connectors → "+ Custom connector" → Remote → fill in Name "Truthifi", URL https://api.truthifi.com/mcp, Description, OAuth 2.0 auth, leave Transport at default → check risk acknowledgement → Add → click Truthifi card to start OAuth → grant scope → done.
Toggle Truthifi on per thread when you want it active. Web-augmented answers and Truthifi-grounded answers can coexist in the same response.
What Perplexity can and can't do with your data
Perplexity can:
Read your account balances, holdings, cost basis, and transaction history.
Read your Truthifi Score and Truthifi findings.
Compute, analyze, summarize, and answer questions across any combination.
Combine portfolio facts with web-search context (current market data, news, fund-specific information).
Cite Truthifi as a source distinct from web sources, so you can see which parts of an answer came from your accounts vs. from public web.
Use connector data inside Perplexity Spaces for ongoing research workflows.
Perplexity cannot:
Initiate trades, transfers, or any money movement.
Modify your Truthifi or brokerage account settings.
Add, remove, or reauthorize financial-institution connections (you do that in Truthifi).
Access your bank or brokerage credentials. They never leave your bank or brokerage.
Persist your data outside of Perplexity's standard conversation retention.
Make decisions for you. Perplexity is good at surfacing facts, doing math, and explaining trade-offs. It is not good at "should I sell" — that's still your call.
The asymmetry is intentional: read-everything, write-nothing. The right shape for an AI assistant connected to your accounts.
This is what AI agents were built for
The original promise of AI agents was assistants that could actually help, not just generate plausible-sounding paragraphs. For most use cases — drafting an email, summarizing a meeting, debugging code — that promise has been delivered. For personal finance, it's been mostly stuck because the agent didn't know your real situation.
Perplexity plus Truthifi closes that gap specifically for users who want an answer engine — one that takes a question, searches whatever's relevant, grounds in your actual data, and returns a citation-backed response. The thing that distinguishes Perplexity from chat-style assistants like Claude or ChatGPT is the search-and-cite design. With Truthifi added, "and your portfolio" becomes a grounded source the same way "and the web" is.
This is also the configuration that holds up best as more financial services expose MCP endpoints — something a number of major institutions are starting to do. As tax software exposes returns, as estate-planning tools expose beneficiary status, as insurance carriers expose policy details, your Perplexity becomes the single answer engine that knows everything you've authorized it to know. Same threading pattern, same citation model, same trust posture.
The longer-term thing worth noting: web context plus your real data is structurally different from either alone. Generic financial advice based on web context is what every LLM does poorly. Account-specific advice without market context is what spreadsheet aggregators do badly. The combination — Perplexity's job — is genuinely useful when both layers are present. Truthifi makes the second layer present.
Perplexity Spaces deserves separate mention. Spaces let you set up persistent research collections that pull from your connected sources every time you open them. With Truthifi connected, you can create a "weekly portfolio review" Space that always greets you with current allocation, top concentrations, recent transactions, and any flagged Truthifi findings — augmented by current market commentary from Perplexity's web layer. That kind of standing dashboard is much more powerful with personal data wired in.
The smartest money move you can make? Hook it up to AI.
Truthifi® tests your finances for 100+ risks and opportunities—automatically. Unlock plain-English insights that drive smarter financial decisions today.
The smartest money move you can make? Hook it up to AI.
Truthifi® tests your finances for 100+ risks and opportunities—automatically. Unlock plain-English insights that drive smarter financial decisions today.
The smartest money move you can make? Hook it up to AI.
Truthifi® tests your finances for 100+ risks and opportunities—automatically.
Frequently asked questions
Do I need a paid Truthifi plan to use this? The free tier connects one financial institution, which is enough to evaluate whether Perplexity-plus-Truthifi delivers useful answers for your situation. Pro and Max plans remove the institution cap and add the analytical layer Truthifi runs on top of raw data — Truthifi Score, fee analysis, and the findings engine. Connection mechanics don't change across tiers.
Do I need a paid Perplexity plan? Yes — custom connectors require Perplexity Pro, Max, or Enterprise. Free Perplexity does not expose the connector flow.
Can I combine Truthifi answers with Perplexity's web-search answers in one response? Yes — that's the design point. Ask a question that requires both, and Perplexity will draw from each layer in the same response. You'll see citations distinguishing Truthifi-sourced content from web-sourced content. This is uniquely Perplexity's strength among AI agents — the explicit-citation pattern means you always know which numbers came from your accounts.
What happens to my Perplexity conversation history? Perplexity stores conversation history per its standard retention policy. Connector responses are not used for training. Truthifi data flowing through threads stays in conversation history per Perplexity's normal rules.
How quickly does Truthifi reflect changes from my brokerage? Truthifi syncs at standard aggregation intervals — typically once per business day for most institutions, real-time or near-real-time for some. When you ask Perplexity about a position that just traded, you'll see the most recent sync, which is usually less than 24 hours stale.
What if I want to add a different MCP server alongside Truthifi? Perplexity supports multiple custom connectors. Add Truthifi for portfolio data and any other MCP-compatible service alongside. They coexist; Perplexity routes queries to whichever connector has the right tool.
Is the connection encrypted end-to-end? Yes. Perplexity talks to Truthifi over HTTPS with TLS. OAuth tokens are stored encrypted on Perplexity. Truthifi's connection to your underlying brokerages goes over their respective secure APIs.
Can I see what tools Truthifi exposes? Yes. Truthifi publishes the tool schema at the MCP endpoint — Perplexity fetches this on connection. From Perplexity's connector detail page you can also see the tools the connector advertises.
What if Perplexity's response contradicts what I see in my brokerage app? Almost always a sync timing issue. Truthifi reflects what the brokerage exposed at last sync; if a trade just settled, Truthifi may not have it yet. Re-ask in a few hours. If discrepancies persist, check the audit log at truthifi.com.
Can I use Truthifi inside Perplexity Spaces? Yes — Spaces inherit your account's connectors, so Truthifi is available in any Space you set up. Especially useful for "portfolio review" or "tax-prep" Spaces that should always pull current portfolio data.
Does Perplexity cite Truthifi differently from web sources? Yes. Perplexity treats connector-sourced data as a distinct citation type. In your answers you'll see Truthifi-sourced numbers tagged differently from web-source citations, so you can verify each layer independently.
Stop asking Perplexity about a hypothetical portfolio
Every minute you spend pasting screenshots into your AI agent is a minute it's working with stale data. Every "could you analyze my situation" prompt that ends with "I don't have access to your accounts" is a friction point that shouldn't exist.
Connect Truthifi → ask Perplexity the question that's been on your list. The setup takes two minutes. The first useful answer pays it back immediately.
Setup guide: How to Connect Your Portfolio to Perplexity via Truthifi MCP.
Citation-rich answer patterns for portfolio queries
Perplexity's signature is the citation-rich, source-transparent answer. With Truthifi connected, that pattern extends to your portfolio data — and the result is genuinely different from chat-style assistants.
Two-source comparisons. Ask Perplexity "compare my expense ratios to industry medians and recent commentary on fee compression in retail mutual funds." A useful response looks like: "You hold 11 mutual funds with median expense ratio 22 bps [Truthifi]. Industry median for actively-managed equity funds is currently 47 bps [ICI 2026 fact book, Morningstar Q1 commentary]. Recent commentary on fee compression [Bloomberg piece, FT analysis] suggests continued pressure toward sub-20 bps for index strategies. Two of your funds (AGTHX at 64 bps, OAKMX at 81 bps) are notably above both your portfolio median and the industry median — flagged for review." Notice the citation pattern: every claim traces to either Truthifi (your data) or a specific public source. Verification is a one-click trace away.
Fact-checked recommendations. Ask "should I be concerned about my bond duration given current Fed guidance?" Perplexity pulls the current Fed posture (web sources with citations), maps it to your actual bond holdings (Truthifi), and reasons about exposure. The answer comes with citations to the specific Fed communications informing the analysis — so if you disagree with one source's interpretation, you can disregard that piece without invalidating the whole answer.
Source-diversified market context. When you ask Perplexity "what does the market think about [stock you hold]," it pulls multiple independent sources rather than relying on any single voice. A response might cite analyst notes from three firms, recent earnings commentary, and one or two financial-press pieces — all visible. You see the consensus and the dissent. Truthifi grounds the discussion in your actual position size, so the analysis is appropriately weighted.
Time-stamped data freshness. Perplexity surfaces when each web source was published or last updated. Truthifi data shows when it was last synced. Both layers carry their own provenance, which means you can immediately spot if a "real-time" question is being answered with stale data on either side. Worth knowing because most "AI for finance" tools fudge the freshness question.
Auditable research workflows in Spaces. Perplexity Spaces persist context. Set up a "weekly portfolio review" Space with Truthifi connected; every time you open it, the prompts run with current data and current public context, with citations preserved across the workflow's history. Useful for accountability and for showing your work — particularly if you're discussing portfolio decisions with a partner or advisor and want to keep a paper trail.
These patterns aren't theoretical. They're how Perplexity's citation-rich design becomes meaningfully different from Claude or ChatGPT once Truthifi is in the loop. The web-context layer was always Perplexity's strength; with personal data added, the strength compounds.
Frequently asked questions
Do I need a paid Truthifi plan to use this? The free tier connects one financial institution, which is enough to evaluate whether Perplexity-plus-Truthifi delivers useful answers for your situation. Pro and Max plans remove the institution cap and add the analytical layer Truthifi runs on top of raw data — Truthifi Score, fee analysis, and the findings engine. Connection mechanics don't change across tiers.
Do I need a paid Perplexity plan? Yes — custom connectors require Perplexity Pro, Max, or Enterprise. Free Perplexity does not expose the connector flow.
Can I combine Truthifi answers with Perplexity's web-search answers in one response? Yes — that's the design point. Ask a question that requires both, and Perplexity will draw from each layer in the same response. You'll see citations distinguishing Truthifi-sourced content from web-sourced content. This is uniquely Perplexity's strength among AI agents — the explicit-citation pattern means you always know which numbers came from your accounts.
What happens to my Perplexity conversation history? Perplexity stores conversation history per its standard retention policy. Connector responses are not used for training. Truthifi data flowing through threads stays in conversation history per Perplexity's normal rules.
How quickly does Truthifi reflect changes from my brokerage? Truthifi syncs at standard aggregation intervals — typically once per business day for most institutions, real-time or near-real-time for some. When you ask Perplexity about a position that just traded, you'll see the most recent sync, which is usually less than 24 hours stale.
What if I want to add a different MCP server alongside Truthifi? Perplexity supports multiple custom connectors. Add Truthifi for portfolio data and any other MCP-compatible service alongside. They coexist; Perplexity routes queries to whichever connector has the right tool.
Is the connection encrypted end-to-end? Yes. Perplexity talks to Truthifi over HTTPS with TLS. OAuth tokens are stored encrypted on Perplexity. Truthifi's connection to your underlying brokerages goes over their respective secure APIs.
Can I see what tools Truthifi exposes? Yes. Truthifi publishes the tool schema at the MCP endpoint — Perplexity fetches this on connection. From Perplexity's connector detail page you can also see the tools the connector advertises.
What if Perplexity's response contradicts what I see in my brokerage app? Almost always a sync timing issue. Truthifi reflects what the brokerage exposed at last sync; if a trade just settled, Truthifi may not have it yet. Re-ask in a few hours. If discrepancies persist, check the audit log at truthifi.com.
Can I use Truthifi inside Perplexity Spaces? Yes — Spaces inherit your account's connectors, so Truthifi is available in any Space you set up. Especially useful for "portfolio review" or "tax-prep" Spaces that should always pull current portfolio data.
Does Perplexity cite Truthifi differently from web sources? Yes. Perplexity treats connector-sourced data as a distinct citation type. In your answers you'll see Truthifi-sourced numbers tagged differently from web-source citations, so you can verify each layer independently.
Stop asking Perplexity about a hypothetical portfolio
Every minute you spend pasting screenshots into your AI agent is a minute it's working with stale data. Every "could you analyze my situation" prompt that ends with "I don't have access to your accounts" is a friction point that shouldn't exist.
Connect Truthifi → ask Perplexity the question that's been on your list. The setup takes two minutes. The first useful answer pays it back immediately.
Setup guide: How to Connect Your Portfolio to Perplexity via Truthifi MCP.
Citation-rich answer patterns for portfolio queries
Perplexity's signature is the citation-rich, source-transparent answer. With Truthifi connected, that pattern extends to your portfolio data — and the result is genuinely different from chat-style assistants.
Two-source comparisons. Ask Perplexity "compare my expense ratios to industry medians and recent commentary on fee compression in retail mutual funds." A useful response looks like: "You hold 11 mutual funds with median expense ratio 22 bps [Truthifi]. Industry median for actively-managed equity funds is currently 47 bps [ICI 2026 fact book, Morningstar Q1 commentary]. Recent commentary on fee compression [Bloomberg piece, FT analysis] suggests continued pressure toward sub-20 bps for index strategies. Two of your funds (AGTHX at 64 bps, OAKMX at 81 bps) are notably above both your portfolio median and the industry median — flagged for review." Notice the citation pattern: every claim traces to either Truthifi (your data) or a specific public source. Verification is a one-click trace away.
Fact-checked recommendations. Ask "should I be concerned about my bond duration given current Fed guidance?" Perplexity pulls the current Fed posture (web sources with citations), maps it to your actual bond holdings (Truthifi), and reasons about exposure. The answer comes with citations to the specific Fed communications informing the analysis — so if you disagree with one source's interpretation, you can disregard that piece without invalidating the whole answer.
Source-diversified market context. When you ask Perplexity "what does the market think about [stock you hold]," it pulls multiple independent sources rather than relying on any single voice. A response might cite analyst notes from three firms, recent earnings commentary, and one or two financial-press pieces — all visible. You see the consensus and the dissent. Truthifi grounds the discussion in your actual position size, so the analysis is appropriately weighted.
Time-stamped data freshness. Perplexity surfaces when each web source was published or last updated. Truthifi data shows when it was last synced. Both layers carry their own provenance, which means you can immediately spot if a "real-time" question is being answered with stale data on either side. Worth knowing because most "AI for finance" tools fudge the freshness question.
Auditable research workflows in Spaces. Perplexity Spaces persist context. Set up a "weekly portfolio review" Space with Truthifi connected; every time you open it, the prompts run with current data and current public context, with citations preserved across the workflow's history. Useful for accountability and for showing your work — particularly if you're discussing portfolio decisions with a partner or advisor and want to keep a paper trail.
These patterns aren't theoretical. They're how Perplexity's citation-rich design becomes meaningfully different from Claude or ChatGPT once Truthifi is in the loop. The web-context layer was always Perplexity's strength; with personal data added, the strength compounds.
Disclaimer: This article is for educational purposes only and does not constitute financial, tax, or legal advice. It should not be construed as a personalized recommendation regarding any investment, financial advisor, or financial product. All calculations use hypothetical scenarios and historical return assumptions; actual results will vary. Past performance does not guarantee future results. Consult a qualified financial professional for guidance specific to your situation. Truthifi is an investment monitoring platform — not a financial advisor, broker-dealer, or tax professional. Truthifi does not manage assets, recommend investments, sell financial products, or provide personalized financial advice. Truthifi earns no revenue from advisor referrals, product commissions, or AUM fees. Statistics and data cited reflect publicly available sources current as of the article's publication date. Sources are linked throughout.
Disclaimer: This article is for educational purposes only and does not constitute financial, tax, or legal advice. It should not be construed as a personalized recommendation regarding any investment, financial advisor, or financial product. All calculations use hypothetical scenarios and historical return assumptions; actual results will vary. Past performance does not guarantee future results. Consult a qualified financial professional for guidance specific to your situation. Truthifi is an investment monitoring platform — not a financial advisor, broker-dealer, or tax professional. Truthifi does not manage assets, recommend investments, sell financial products, or provide personalized financial advice. Truthifi earns no revenue from advisor referrals, product commissions, or AUM fees. Statistics and data cited reflect publicly available sources current as of the article's publication date. Sources are linked throughout.
Disclaimer: This article is for educational purposes only and does not constitute financial, tax, or legal advice. It should not be construed as a personalized recommendation regarding any investment, financial advisor, or financial product. All calculations use hypothetical scenarios and historical return assumptions; actual results will vary. Past performance does not guarantee future results. Consult a qualified financial professional for guidance specific to your situation. Truthifi is an investment monitoring platform — not a financial advisor, broker-dealer, or tax professional. Truthifi does not manage assets, recommend investments, sell financial products, or provide personalized financial advice. Truthifi earns no revenue from advisor referrals, product commissions, or AUM fees. Statistics and data cited reflect publicly available sources current as of the article's publication date. Sources are linked throughout.
Ready to get started?