Skip to content

Rank #6 of 7 in Banking Data APIs

Plaid logo

Plaid

YC S13

Plaid Inc. · commercial

58643/yrnpm 828.5k/wk

Try itExperimental

See what an agent can do with Plaid before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -si -X POST https://production.plaid.com/accounts/balance/get -H 'Content-Type: application/json' -d '{}' # keyless → 400 naming the missing client_idrecorded session — replayed, not live
recorded 2026-09-15 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Account linking — stories about account linking in this arenaAccount linkingevidence →

Stories about account linking in this arena

39.4/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

24.9/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

10.3/100

Balance ownership — stories about balance ownership in this arenaBalance ownershipevidence →

Stories about balance ownership in this arena

80.0/100

Banking agent access — stories about banking agent access in this arenaBanking agent accessevidence →

Stories about banking agent access in this arena

33.6/100

Consent security — stories about consent security in this arenaConsent securityevidence →

Stories about consent security in this arena

4.0/100

Data freshness — stories about data freshness in this arenaData freshnessevidence →

Stories about data freshness in this arena

52.0/100

Institution coverage — stories about institution coverage in this arenaInstitution coverageevidence →

Stories about institution coverage in this arena

20.4/100

Integration dx — sandboxes, test modes, webhooks, and how fast a developer gets to a working integrationIntegration dxevidence →

Sandboxes, test modes, webhooks, and how fast a developer gets to a working integration

59.1/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

8.6/100

Payment initiation — stories about payment initiation in this arenaPayment initiationevidence →

Stories about payment initiation in this arena

18.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Transactions enrichment — stories about transactions enrichment in this arenaTransactions enrichmentevidence →

Stories about transactions enrichment in this arena

34.3/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 53/53 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial7/10T

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial7/10T

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/a0/10

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/auntestednone yet

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10C

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10C

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10C

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial3/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1full8/10C

A sandbox with test institutions and documented test credentials lets me exercise linking, data retrieval, and error states end-to-end before touching a real bank account C

Sandbox

developerIntegration dx — sandboxes, test modes, webhooks, and how fast a developer gets to a working integrationIntegration dx3full9/10C

Fetch a real-time balance for a connected account before initiating a payment — a documented balance endpoint intended for NSF and risk checks C

Balances

developerBalance ownership — stories about balance ownership in this arenaBalance ownership3full8/10C

Let a user connect their bank with a drop-in hosted flow — create a session server-side, open the widget, and get back a token for the connected account — without building institution UI myself C

Hosted flows

developerAccount linking — stories about account linking in this arenaAccount linking3full8/10C

Obtain verified account and routing numbers (or tokenized equivalents) from a linked account to fund ACH or bank-debit payments without micro-deposits C

Ach details

developerBalance ownership — stories about balance ownership in this arenaBalance ownership3full8/10C

Pull transaction history for a connected account through the API — paginated, with documented history depth and a sync pattern for fetching only what changed C

Transactions

developerTransactions enrichment — stories about transactions enrichment in this arenaTransactions enrichment3full8/10C

An agent can operate the platform — create link sessions, retrieve balances and transactions, and manage connections through the API or an MCP surface with scoped credentials C

Agent operations

ai-native userBanking agent access — stories about banking agent access in this arenaBanking agent access3partial6/10T

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial4/10C

The platform documents how many institutions it reaches and where — published coverage numbers and geographies I can check against where my users actually bank C

Coverage

founderInstitution coverage — stories about institution coverage in this arenaInstitution coverage3partial3/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3n/auntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3n/auntestednone yet

Data changes arrive as signed webhooks — new transactions, balance updates, connection state changes — so my system stays current without polling C

Webhooks

developerData freshness — stories about data freshness in this arenaData freshness2full8/10C

Linked accounts plug into my payment processor — documented integrations or token exchange that hand verified account credentials to third-party processors and platforms C

Processor tokens

developerBalance ownership — stories about balance ownership in this arenaBalance ownership2full8/10C

Retrieve account-holder details — names, addresses, contact data on file at the bank — to match the account owner against my customer C

Ownership

ops leadBalance ownership — stories about balance ownership in this arenaBalance ownership2full8/10C

Go from signup to my first linked sandbox account fast — self-serve API keys, a runnable quickstart, and client libraries in my language C

Quickstart

developerIntegration dx — sandboxes, test modes, webhooks, and how fast a developer gets to a working integrationIntegration dx2partial7/10T

Initiate a bank payment from a connected account — a documented pay-by-bank or payment-initiation product with its live geographies stated honestly C

Pay by bank

developerPayment initiation — stories about payment initiation in this arenaPayment initiation2partial6/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial5/10T

One link session can power multiple data products — auth, balances, transactions, identity — without forcing the user through separate connection flows per product C

Multi product

developerIntegration dx — sandboxes, test modes, webhooks, and how fast a developer gets to a working integrationIntegration dx2partial5/10C

The data comes back agent-consumable — clean structured JSON, documented schemas, and enrichment an automated financial workflow can reason over without heuristic parsing C

Agent data

ai-native userBanking agent access — stories about banking agent access in this arenaBanking agent access2partial5/10T

I request only the data scopes I need — product-scoped consents and documented data-minimization controls, not an all-or-nothing grant C

Scopes

developerConsent security — stories about consent security in this arenaConsent security2disputed4/10D

Per-institution health is visible — documented institution statuses, outage or degradation signals, and error codes that distinguish a bank problem from my problem C

Status

ops leadInstitution coverage — stories about institution coverage in this arenaInstitution coverage2partial4/10T

Trigger an on-demand refresh of a connected account's data through the API when my use case needs now-fresh data, with the refresh semantics documented C

Refresh

developerData freshness — stories about data freshness in this arenaData freshness2partial4/10C

Broken connections are repairable — expired or revoked links surface as documented statuses, and users can re-authenticate in an update flow without starting over C

Repair

ops leadAccount linking — stories about account linking in this arenaAccount linking2partial3/10C

Connections to major institutions use bank-hosted OAuth rather than screen-scraped credentials — the platform documents its OAuth coverage and how legacy credential flows are being retired C

Oauth

developerAccount linking — stories about account linking in this arenaAccount linking2none0/10

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2none0/10

End users can see and revoke what they've shared — a documented consent surface or portal where a user manages which apps hold access to their bank data C

Consent

ops leadConsent security — stories about consent security in this arenaConsent security2none0/10

Raw bank transactions come back enriched — cleaned merchant names, categories, and logos — documented as a capability of the platform, not left as an exercise for me C

Enrichment

developerTransactions enrichment — stories about transactions enrichment in this arenaTransactions enrichment2none0/10

Recurring bank payments are supported — variable recurring payments, standing consents, or documented recurring debit flows built on the connection C

Recurring

developerPayment initiation — stories about payment initiation in this arenaPayment initiation2none0/10

Sever and clean up — a documented way to delete a connection or user and have the platform stop collecting and purge held data C

Deletion

ops leadConsent security — stories about consent security in this arenaConsent security2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

The platform derives income and cash-flow signals from connected accounts — recurring streams, payroll detection, or documented income verification products built on the same data C

Cashflow

finance leadTransactions enrichment — stories about transactions enrichment in this arenaTransactions enrichment2noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1n/auntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 37 stories with headroom

What would move Plaid’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".

  2. Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the product

    nonemoves Built-in AIimpact 30

    Missing: any AI/ML insight-generation feature, natural-language summarization of transactions/balances, or user-facing recommendation engine.

  3. Agenticness — how well agents can access and operate the productUse an official CLI

    nonemoves agent-readyimpact 30

    Evidence shows Plaid SDKs (e.g., plaid-node), Quickstart apps, and a hosted MCP server, but no mention anywhere of an official CLI tool for interacting with Plaid's API or dashboard.

  4. Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent

    nonemoves agent-readyimpact 30

    Missing: any documentation of scoped API keys, credential minimization, or agent-specific access tokens.

  5. Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples

    nonemoves API qualityimpact 30

    Evidence shows only static docs pages, a Quickstart sample app to clone locally, and a Sandbox test environment, but no interactive API reference (e.g., try-it console, embedded runnable code snippets) — probes for an OpenAPI spec and docs-as-markdown interactive surface both returned 404s, suggesting no such interactive reference exists.

  6. Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)

    nonemoves API qualityimpact 30

    Direct probes for OpenAPI/swagger spec files at standard paths all returned 404, and no documentation references a downloadable machine-readable API spec; only an llms.txt marketing page was found, not an OpenAPI/equivalent spec.

  7. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    The evidence pack contains no documentation of API versioning scheme or a deprecation policy — no changelog, version headers, or sunset timeline are mentioned anywhere, only product feature docs (Auth, Balance, Identity, Transactions) and SDK error-handling snippets.

  8. Institution coverage — stories about institution coverage in this arenaThe platform documents how many institutions it reaches and where — published coverage numbers and geographies I can check against where my users actually bank

    partialq3/10moves PA Scoreimpact 21

    Missing: published total institution count, per-country/region coverage breakdown, and any independent verification of coverage claims.

Showing the top 8 of 37 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map5 surfaces · 29 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

docs29 stories

GitHub README14 stories

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -si -X POST https://production.plaid.com/accounts/balance/get -H 'Content-Type: application/json' -d '{}' # keyless → 400 naming the missing client_idreproduced
$ curl -si -X POST https://production.plaid.com/accounts/balance/get -H 'Content-Type: application/json' -d '{}'  # [redacted]less → 400 naming the missing client_id
HTTP/1.1 400 Bad Request

Server: nginx
$curl -sL https://plaid.com/docs/llms.txt | head -3reproduced
$ curl -sL https://plaid.com/docs/llms.txt | head -3
# Plaid Technical Documentation

# Full version: https://plaid.com/docs/llms-full.txt
$curl -s -X POST https://api.dashboard.plaid.com/mcp/sse -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # the Dashboard MCP Plaid documents (OAuth mcp:dashboard scope)reproduced
$ curl -s -X POST https://api.dashboard.plaid.com/mcp/sse -H 'Content-Type: application/json' -d '<jsonrpc initialize>'  # the Dashboard MCP Plaid documents (OAuth mcp:dashboard scope)
{"error":"Unauthorized"}

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

2 of 13 testable claims verified · 0 contradictedintegrity 15/100

15 distinct capability claims found in Plaid’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

2

Verified

11

Unverified

0

Contradicted

15

Undersold

Verified (2)
Unverified (13)
Undersold (15)
Claims outside our story set (1)

Real capability claims found in Plaid’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • Dashboard lets you customize parts of the Link flow with real-time preview and instant publish to production

    source ↗
Suggest a story for these →

Business model

usage-basedenterprise-custom

Tiers named, numbers not published: a free limited-production tier (200 API calls per product on live data), Pay as You Go, Growth, and Custom — real prices arrive with the sales conversation.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Scoretracked since Sep 15 '26 — no movement recorded yet
Agent-readytracked since Sep 15 '26 — no movement recorded yet

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

Data