# Fix list: Keycard From Anchor Terminal's listing at https://www.anchorterminal.com/tools/keycard, the October 2026 research run, assessed 1 October 2026. Grade C, 56.3 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 Keycard: 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, 35 out of 100, up to 13 more on the total Why it scored 35: A status page exists at status.keycard.ai and describes itself as real-time and historical system health (20). Its history renders client-side and its JSON and RSS feeds returned 403 to our reader on 1 and 2 October, so we couldn't read the last 90 days (5). The docs index, 73 entries on 2 October, has no rate limit page (0). We found no 429 or back-off guidance, only the `insufficient_authorization` error that tells an agent to stop (0). The pricing page lists an SLA on Team and 99.95 per cent uptime on Enterprise (10). The quickstart still calls Keycard Early Access and sends sign-up to a form that asks you to request an account, so the surface isn't GA (0). 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, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). Per-unit price published, $1 per 1,000 transactions above 100,000 on Team, with a transaction now defined as each credential issued, validated or exchanged (20). Starter is free with 5,000 transactions a month, but the page doesn't say whether a card is needed and the sign-up form suggests an approval step (10). A person signs up in a browser (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. Agent ergonomics, 60 out of 100, up to 6.5 more on the total Why it scored 60: A token exchange returns one short-lived credential, so there's nothing to size (20). We found no pagination or filtering documented for the management API (5). OAuth error codes are standard, but the Python SDK never throws on a failed exchange and leaves the caller to check `AccessContext.has_errors()` (12). An exchange is safe to repeat, though nothing says so (8). SDKs in Python and TypeScript with FastMCP and LangChain integrations and few required settings (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. ## 4. Schema & documentation, 61 out of 100, up to 6.3 more on the total Why it scored 61: No public OpenAPI file, though the REST client is generated from one, and the zone publishes standard OAuth discovery metadata at `/.well-known/oauth-authorization-server` (10). llms.txt and Markdown docs (10). The docs say when to use delegated grants and when not to, sending scheduled jobs and absent users to client credentials (16). Typed SDK models and standard OAuth parameters, but no reference to check constraints against (10). Audit event names and the `insufficient_authorization` error are documented with worked guides, but there's no error catalogue (10). No public changelog, only CHANGELOG.md files in the SDK repositories (5). 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. ## 5. Transparency & trust, 45 out of 100, up to 4.8 more on the total Made of editorial 25, provenance 65. Why it scored 45: SDKs under MIT and Apache-2.0, but there's no terms of service for the platform. keycard.ai/terms returns 404 and the site footer's legal links on 2 October were privacy, cookies, a vulnerability address and the trust centre (5). Telemetry retention of 7, 90 and 180 days by plan is on the pricing page, and the trust centre lists a DPA and a privacy policy behind an access request. The privacy page's body still didn't load for us (10). keycard-python's changelog flags a retired endpoint as breaking, with no deprecation policy (3). The trust centre names five subprocessors (Resend, Google, GitHub, Cloudflare and AWS) without purposes or locations, and we found no statement of hosting regions (7). 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): - Domain age: keycard.ai, no registry record we could read (0 of 15) - Terms of service: not found (0 of 10) - Changelog: not found (0 of 10) ## 6. Security & auth, 86 out of 100, up to 2.5 more on the total Why it scored 86: OAuth 2.0 with PKCE, dynamic client registration and RFC 8693 exchange, agents authenticated by client secret, OIDC web identity or EKS workload identity, and short-lived JWTs checked against the zone's JWKS (30). Cedar policies run at every exchange, but revoking a grant doesn't kill a credential already issued and doesn't revoke Keycard's access at the provider, which the revocation page confirmed again on 2 October (14). The service returns credentials, not untrusted content (10). Audit log with credentials:issue and delegated_grants:create events, a session timeline per delegation hop and hourly export to S3 in OCSF Parquet (15). security.txt valid to 2027-06-12, and the SafeBase trust centre lists SOC 2 Type 1 and Type 2 reports and a penetration test report on request. No bug bounty or public advisories found (17). 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. ## 7. Maintenance & community, 79 out of 100, up to 1.8 more on the total Why it scored 79: keycard-python 0.18.0 on 22 September 2026 and keycardai-mcp 2.3.2 on 16 September (30). keycardai-mcp alone shipped eight releases between 30 July and 16 September 2026 (20). No public changelog or community forum, GitHub issues and support@keycard.ai as the channels, and 10 open pull requests on python-sdk (7). Python and TypeScript SDKs are current (15). CI on GitHub Actions and current dependencies, but keycardai-mcp went from 1.0.0 to 2.0.0 in a day, on 6 and 7 August 2026 (7). 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: the status page's incident history. It renders client-side and its JSON and RSS feeds returned 403 to our reader on 1 and 2 October, so reliability carries 5 rather than a real incident score. - unchecked: the privacy policy body, which didn't load on 30 September or 2 October. The DPA sits behind an access request in the trust centre. - No terms of service found, and no hosting regions or subprocessor locations. - Whether Starter needs a card. Sign-up is by request during Early Access, per the quickstart and the pricing page's form. ## Weaknesses - Early Access with sign-up by request, and no terms of service page - No per-token kill switch, so a revoked grant lives until the token expires, and revocation doesn't reach the provider - No published rate limits, 429 guidance or public changelog - keycardai-mcp went from 1.0.0 to 2.0.0 in a day in August 2026 - Team is $500 a month with nothing between it and the free tier ## 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. - Set audience to the server's registered resource identifier, or the verifier accepts tokens minted for any resource in the zone - Check `AccessContext.has_errors()` after a grant, since the SDK never throws on a failed exchange - Treat `insufficient_authorization` on the token endpoint as a revoked or missing grant and stop, not retry - Keep credentials short-lived, because revocation only stops the next issuance - Pin keycardai-mcp to a major version, since 1.0.0 and 2.0.0 shipped a day apart ## What the review panel asked for - Self-serve sign-up - A stated approval turnaround - per-token revocation - published terms of service ## 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.