ComplyAdvantage

# Fix list: ComplyAdvantage

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/complyadvantage, the October 2026 research run, assessed 8 October 2026. Grade D, 52.6 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 ComplyAdvantage: 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. Reliability, 42 out of 100, up to 11.6 more on the total

Why it scored 42: Graded on the Mesh REST API, hosted lines. No public status page was found. status.complyadvantage.com does not resolve and none is linked from the site, the docs or the help centre (0). No readable incident history (5). Default limits published as 1,000 requests a minute in production and 300 in Sandbox (15). `Ratelimit-Limit`, `Ratelimit-Remaining` and `Ratelimit-Reset` headers are documented, an idempotency key header exists on the rescreen workflow and two workflows are described as safe to resend, but the Mesh docs give no backoff guidance (12). No SLA found in public (0). The API is generally available (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.

## 2. Payments & pricing, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No x402, MPP or L402 (0). Starter Plan prices are public by monitored-entity tier, from $119 a month, and Enterprise is priced on application. No per-call price (10). No free tier or trial was found. Sandbox comes with a paid account, and ComplyLaunch is free only to start-ups accepted on application (0). A person buys the plan and staff set the account up within a working day (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.

## 3. Maintenance & community, 28 out of 100, up to 6.3 more on the total

Why it scored 28: No changelog or release notes were found, so dates come from docs page timestamps. The getting started guide was updated on 16 September 2026, the rate limiting guide on 28 August and the `/v3/token` reference on 12 August. Scored as within 90 days because a page edit is weaker evidence than a release (20). No dated changelog entries (0). Support by email and a ticket portal, with a help centre whose credential article was updated in September 2026. No public community channel found (5). No official SDK (0). The OpenAPI spec and Postman collection are current with the reference pages (3).

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.

## 4. Security & auth, 68 out of 100, up to 5.6 more on the total

Why it scored 68: OAuth2 client credentials with per-credential permissions, optional expiry, 24-hour tokens and deactivation that invalidates issued tokens. Credentials can't be edited, and the older username and password token flow is still supported (28). View and manage permissions are separate and a creator can only grant permissions they hold. No confirmation step for deletes was found (14). Results include third-party adverse media text and customer-supplied data. No injection guidance was found (3). Audit log endpoints for the account, cases, customers, roles, transactions and users (14). ISO 27001 and SOC 2 are stated in the vendor's own article of January 2025, with CREST penetration testing. No security.txt, disclosure policy, bug bounty or trust centre was found (9). No deduction for the older API accepting a key in the query string, because the graded Mesh API takes the token in a header only.

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.

## 5. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: List responses are partial records sized with `page_size`. No field selection was found (15). `page_number`, `page_size`, attribute, range and substring filters and `sort` on 48 operations, described as most list endpoints (18). Errors follow one structure with title, status, detail, an identifier and a timestamp (16). `X-ComplyAdvantage-Idempotency-Key` on one operation, two workflows described as idempotent, and 409 on concurrent requests for one external identifier (12). No official SDK was found, and a token must be fetched every 24 hours. A Postman collection is published (6).

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.

## 6. Transparency & trust, 50 out of 100, up to 4.4 more on the total

Made of editorial 40, provenance 59.

Why it scored 50: Closed service. The only public terms cover the website, and no service agreement or API terms were found (8). The privacy notice of 12 June 2026 sets out controller and processor roles, transfer safeguards and 30-day backup retention for removed database entries. No public data processing agreement or retention period for customers' screening data was found (14). A versioning policy lists what counts as backwards compatible, the older API's 2018 deprecation gave two years' notice with dates, and the Mesh spec marks 5 operations deprecated without dates (10). Six regional API hosts are named in the webhooks guide. No subprocessor list was found (8).

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: not found (0 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Schema & documentation, 82 out of 100, up to 2.9 more on the total

Why it scored 82: Public OpenAPI 3.0.3 spec with 165 operations on 124 paths (25). `llms.txt` and every docs page as Markdown (10). All 165 operations carry a summary and description, 124 name the permission needed, and some say when to use another endpoint, such as exports above 10,000 customers (15). 949 schemas with 441 enums and 682 required lists (13). 1,361 examples and an errors guide with a body for each status, though 429 is not declared on operations (12). A versioning policy and `/v2` and `/v3` paths, but no changelog was found (7).

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.

## 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.

- The lead's docs link, docs.complyadvantage.com, is the older API. New integrations are documented on Mesh at docs.mesh.complyadvantage.com, which is the surface graded. The 300 calls a minute Sandbox limit holds for both.
- Whether new customers can still be given the older API was not established.
- No status page was found. A private or customer-only page may exist.
- No service agreement, API terms, data processing agreement, SLA or subprocessor list was found in public, so `provenance.terms` is left out.
- unchecked: the Starter Plan checkout page at https://complyadvantage.com/checkout/ is drawn by script, so any terms linked from it were not read.
- unchecked: the Mesh web application and support portal need a login, so credential permission names and any in-app release notes were not read.
- No official SDK was found in the docs. Package registries were not searched for unofficial clients.
- ISO 27001 and SOC 2 rest on the vendor's own article of 21 January 2025. No certificate or report was seen.

## Weaknesses

- No public status page or incident history was found. `status.complyadvantage.com` does not resolve
- No changelog or release notes were found for the Mesh API
- No service agreement, data processing agreement or subprocessor list is published. The terms page covers the website only
- No free tier or self-serve trial. The Starter Plan starts at $119 a month and accounts are set up by staff within a working day
- No official SDK was found. Access tokens last 24 hours with no refresh
- Screening results carry third-party adverse media text, and no prompt-injection guidance was found

## 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.

- Exchange the access key and secret at `POST /v3/token` for a bearer token. It lasts 24 hours and can't be refreshed, so request a new one before expiry
- Ask for a credential with only the permissions the task needs. Permissions can't be edited later, and each reference page names the ones a call requires
- Create a screening configuration first and keep its `configuration_identifier`. Creating and screening a customer needs it
- Give each customer a unique external identifier. A concurrent request for the same identifier returns 409 with a pointer to the first workflow
- Read `Ratelimit-Remaining` and `Ratelimit-Reset` on every response. A 429 body is only `API rate limit exceeded`

## 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.