Plaid Identity Verification

# Fix list: Plaid Identity Verification

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/plaid-identity-verification, the October 2026 research run, assessed 14 October 2026. Grade B, 67.1 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Plaid Identity Verification: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 15 out of 100, up to 10.6 more on the total

Why it scored 15: No x402, MPP or L402 (0). The pricing page lists Identity Verification under Pay as you go, Growth and Custom with no prices, and the docs say exact pricing appears after applying for Production. The fee model (a base Anti-Fraud Engine fee plus data source, document and selfie fees) has no numbers (0). Sandbox access for Identity Verification became self-serve on 12 August 2026 from the Dashboard Products page, with no card per the plaid listing (15 of 20). A person signs up in a browser, and Production needs a product access request (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Security & auth, 61 out of 100, up to 6.8 more on the total

Why it scored 61: `client_id` and `secret` in the JSON body, separate secrets per environment, rotatable from the Dashboard. No scopes on the secret (20 of 30). One secret reaches every Plaid product the team has, with no read-only key. Redaction of personal data runs on a custom schedule set by Plaid support, not by API (8 of 20). Responses carry user-entered and document data, with no injection guidance (5 of 15). Dashboard request logs for 14 days and Dashboard audit logs since August 2025 (13 of 15). security.txt valid until 31 December 2026 with a HackerOne programme. No SOC 2 or ISO 27001 statement on the pages read (15 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 3. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Read with the hosted lines. status.plaid.com is a Statuspage with API Production and Sandbox components and per-bank components, and no component of its own for Identity Verification (20). Between 16 July and 14 October 2026 one incident names Identity Verification, the Python SDK (v33.0.0 and later) degraded when retrieving results on 1 August for 82 minutes, marked minor. Plaid's own API had elevated errors on 24 August, also minor. The majors in that window are single banks and the Dashboard, which this product doesn't depend on (20). Rate limits are on plaid.com/docs/errors/rate-limit-exceeded, a path Plaid's robots.txt disallows, so we didn't read it. The plaid listing's 30 September check found limits published per endpoint, and whether Identity Verification endpoints are among them is unconfirmed (10 of 15). A 429 returns RATE_LIMIT_EXCEEDED with no Retry-After per the plaid listing, and `/identity_verification/create` takes `is_idempotent: true`, which returns the existing session instead of creating a second (8 of 15). No SLA found (0). The product is generally available, with the AAMVA check in beta (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 4. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: Four endpoints. Responses are large, with every check's result in one object and no field selection (12 of 25). `/identity_verification/list` takes a cursor and filters by `client_user_id` and `template_id`, both required (15 of 20). Errors carry `error_type`, `error_code`, `request_id`, `display_message` and a documentation URL (20). Create takes `is_idempotent`, so a retry returns the existing session, and reads are safe to repeat. Retries are billed as new sessions (16 of 20). Official SDKs in several languages. Most checks need the end user in Plaid Link, while the backend-only flow runs data source checks with no UI (12 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Transparency & trust, 77 out of 100, up to 2 more on the total

Made of editorial 57, provenance 97.

Why it scored 77: Closed service under Plaid's published developer policy and end-user terms. SDKs are MIT (15 of 30). The docs say Identity Verification keeps session data while the contract is active, allows a rolling redaction period on request and ends Dashboard and API access when the contract ends, so data must be exported first. No retention period is stated by default (18 of 30). Dated deprecations in the changelog (16 of 20). Data from the UK and EEA goes to the US per the plaid listing. No named sub-processor list found (8 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10)

## 6. Schema & documentation, 91 out of 100, up to 1.5 more on the total

Why it scored 91: Plaid's public OpenAPI file (plaid/plaid-openapi, version 2020-09-14_1.762.0) has the four `/identity_verification` operations and the `/watchlist_screening` operations for Monitor (25). llms.txt and a Markdown twin of each docs page (10). Field descriptions say how to use them, for example that the DOB check runs synchronously and shouldn't be polled, and the guides explain the backend-only flow and when to use documents as a fallback (16 of 20). Typed request and response objects with enums for status and check results (13 of 15). curl examples on every endpoint. The error pages sit under /docs/errors/, which robots.txt disallows, so we read error handling only from the reference (12 of 15). Dated API version and a changelog with Identity Verification entries (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 7. Maintenance & community, 83 out of 100, up to 1.5 more on the total

Why it scored 83: The changelog's latest Identity Verification entry is 13 October 2026 (SSA match result in `kyc_check`) (30). Six Identity Verification entries since 9 July, on 9 July, 17 July, 12 August, 3 September, 24 September and 13 October (20). A closed service with a dated changelog and Dashboard support (12 of 15). plaid-node 48.0.0 on 6 October 2026, regenerated from the OpenAPI file (15). plaid-node has no test workflow in its repository per the plaid listing (6 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: plaid.com/docs/errors/rate-limit-exceeded and the other /docs/errors/ pages, which robots.txt disallows for all crawlers. Rate limits and error codes for Identity Verification endpoints come from the plaid listing's 30 September check and the API reference only. Under the brief this may mean the listing should be held
- Whether the Sandbox sign-up asks for a card. Per the plaid listing it doesn't
- Watchlist screening runs through Monitor, sold as a separate product. Capability kyc.screening is listed because an Identity Verification template can include a Monitor screening step
- Plaid's Dashboard MCP server covers Production diagnostics and analytics. No Identity Verification tools were confirmed and we didn't call it

## Weaknesses

- No public prices. Rates appear only after a Production application
- One team secret reaches every Plaid product, with no scopes or read-only key
- Integrating companies must be based in the US, Canada or the UK
- Data stays only while the contract is active, and access to past sessions ends with it
- Rate-limit and error pages sit under a path robots.txt disallows, so we didn't read them

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Pass `is_idempotent: true` to /identity_verification/create so a retry returns the existing session
- Use the backend-only flow (data source template, `gave_consent: true`) when you already hold the user's details. Documents and selfies need the person in Link
- Wait for the STATUS_UPDATED webhook or poll /identity_verification/get. Link's onSuccess doesn't mean the user passed
- Don't issue retries casually. Each retry is a new session billed again
- Enable Sandbox for Identity Verification on the Dashboard Products page before the first call

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.