Clay

# Fix list: Clay

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/clay, the October 2026 research run, assessed 14 October 2026. Grade C, 57.7 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 Clay: 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, 45 out of 100, up to 11 more on the total

Why it scored 45: Graded with the hosted lines on the Public API. status.clay.com exists but answered with a bot check, so we couldn't confirm components (10 of 20). No readable history (5). A per-workspace request limit with no number, and published search-result caps per plan (8 of 15). 429 with Retry-After and X-RateLimit headers, backoff with jitter, and retry guidance only when a request is safe to retry. No idempotency keys (12 of 15). The terms set a 99.0 per cent monthly uptime target with credits for six-hour outages, a target rather than a guarantee (5 of 10). The API is v0, and Workflows and run search are labelled alpha or beta (5 of 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. Security & auth, 48 out of 100, up to 9.1 more on the total

Why it scored 48: A personal API key tied to the user's workspace access, with no scopes documented. The CLI uses OAuth per workspace (15 of 30). Functions need API or MCP access switched on one by one and workspace roles apply, but the Claude Code plugin's hook auto-approves most clay CLI commands, including ones that spend credits (8 of 20). Claygent web research returns untrusted text, and no injection guidance was found (3 of 15). Credit balances and a workflow-run query, with no per-call audit log found (6 of 15). Valid security.txt to July 2027, a trust centre, and SOC 2 Type II, ISO 27001 and ISO 42001 listed. No bug bounty found (16 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. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Data credits from $0.05 and plan prices public, though the plan cards and the FAQ disagree on the Launch and Growth prices (15 of 20). A free plan described as "no strings attached", with a card requirement not stated on the page (15 of 20). A person signs up in a browser, and CLI sign-in opens a browser or a device code (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.

## 4. Agent ergonomics, 66 out of 100, up to 5.5 more on the total

Why it scored 66: Table queries select fields and take a limit, and searches return up to 500 per request (20 of 25). Cursor pagination and stateful iterators, structured filters and an advanced query language (20). Status codes as the error category and a message, with no stable codes in the API, though the CLI has typed exit codes (10 of 20). Items carry caller IDs for matching results and failed enrichments aren't charged, but there are no idempotency keys (8 of 20). No official SDKs, and the CLI is JSON-first (8 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, 64 out of 100, up to 3.2 more on the total

Made of editorial 28, provenance 99.

Why it scored 64: Closed service under terms dated 23 May 2024, and a plugin repository with no licence (12 of 30). The privacy policy dates from 11 September 2020, gives no retention periods and says nothing on AI training, and doesn't describe an opt-out for people whose data comes from Clay's providers (8 of 30). Deprecated endpoints are marked in the spec without removal dates (8 of 20). No sub-processor list found (0).

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 (9.1 of 10)

## 6. Schema & documentation, 84 out of 100, up to 2.6 more on the total

Why it scored 84: A public OpenAPI 3 spec with 16 operations (25). llms.txt and Markdown copies of every page (10). Pages say when to use each primitive, and deprecated filters-mode endpoints name their replacement (16 of 20). Typed request bodies, with a query grammar fetched from a reference endpoint rather than enums (12 of 15). curl examples on every guide, but error bodies carry only a message with no stable codes (9 of 15). v0 in the path and a weekly product changelog that names CLI and MCP changes, without an API-specific log (12 of 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, 75 out of 100, up to 2.2 more on the total

Why it scored 75: clay plugin 2.32.0 with CLI 1.9.0 on 6 October 2026 (30). Plugin releases on 25 September, 1, 2 (two) and 6 October (20). Weekly dated product roundups and a support address, with the plugin's issue handling not visible (12 of 15). No official SDKs, the CLI is current (8 of 15). CLI binaries ship from GitHub releases, and the repository has no licence file (5 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: status.clay.com components and incident history, which sat behind a bot check
- unchecked: the Clay MCP endpoint, its authentication and tool list, which have no public reference
- Whether the Public API is limited to Enterprise as the pricing FAQ says, or open to all plans as the developer docs imply
- unchecked: trust.clay.com and privacy.clay.com, including any sub-processor list

## Weaknesses

- API keys carry no scopes and act with the user's workspace access
- The Claude Code plugin auto-approves most clay CLI commands, including ones that spend credits
- No request-rate number published, and error bodies have no stable codes
- Privacy policy dated September 2020 with no retention periods
- Pricing page gives two different prices for Launch and Growth, and says API access is Enterprise

## 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.

- Fetch GET /search/query-mode/reference before writing a search query
- Poll routine results until a terminal 200, since 202 means still running
- Expect HTTP 402 when a plan's search cap is hit, and tell the user the reset date
- Check GET /credits/balance before large batch runs
- Ask the user before enabling the plugin's auto-approve hook in a shared workspace

## 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.