# Fix list: Airtable From Anchor Terminal's listing at https://www.anchorterminal.com/tools/airtable, the October 2026 research run, assessed 8 October 2026. Grade BB, 70.9 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 Airtable: 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, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 found (0). Plan prices are public, Team at $20 and Business at $45 a seat a month billed annually, with monthly API call allowances per plan and no per-call price (10). A Free plan with 1,000 API calls a month per workspace, and the pricing page mentions cards only for paid plans. We didn't complete a signup (20). A person signs up in a browser and creates a token or approves OAuth (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. Agent ergonomics, 68 out of 100, up to 5.2 more on the total Why it scored 68: The MCP server documents 40 tools with no toolsets or dynamic loading found (5 of 25), while the REST API sizes responses with `fields`, `pageSize` and `maxRecords`, so 12 overall. Offset pagination up to 100 records a page, with `filterByFormula`, `sort` and `view` (20). Error bodies carry a type and message, such as INVALID_PERMISSIONS naming the table or field (16). No idempotency keys. `performUpsert` with up to three merge fields, an MCP `revert_action` tool, and a CLI that labels each tool read-only, write or destructive from the server's annotations, which we didn't read first-hand (12). Few required parameters, but airtable.js is the only official client and its last release was v0.12.2 on 16 August 2023. Python clients are community-built (8). 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. ## 3. Maintenance & community, 49 out of 100, up to 4.5 more on the total Why it scored 49: Newest dated release is @airtable/mcp-cli v0.2.9 on 7 August 2026, 62 days before the check. The Web API changelog was last updated on 24 June 2026 (20). One dated release in the last 90 days (0). Public changelog, a developer community forum and a help centre. We didn't read reply times, and airtable.js shows 145 open issues with its last commit on 6 June 2025 (8). Listed in the official MCP registry as com.airtable/mcp, active since 8 May 2026 (15). The CLI repository has CI, release and Dependabot workflows, while airtable.js has had no release since August 2023 (6). 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. Schema & documentation, 73 out of 100, up to 4.4 more on the total Why it scored 73: No OpenAPI description was found in the reviewed documentation. The MCP server publishes its tool list over the protocol, which we couldn't read without an account (10 of 25). llms.txt files at airtable.com/developers and a Markdown copy of every reference page (10). Each endpoint page states scope, user role and plan, and the MCP tools reference gives purpose, ordering hints such as calling `list_automations` first, and limits such as no field type changes (16). Parameters are typed with enums and required flags, but cell values are untyped objects keyed by field name and filters are formula strings (11). Curl examples with responses on endpoint pages, and an errors page with sample bodies for 403, 404, 422, 429 and 503 (13). One API version (v0) with a dated changelog, 6 entries in 2026, the latest on 24 June (13). 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. Security & auth, 78 out of 100, up to 3.9 more on the total Why it scored 78: OAuth 2.0 with PKCE, 60-minute access tokens and rotating 60-day refresh tokens, or personal access tokens, both limited by scope and by base or workspace. Secrets in the legacy `api_key` URL parameter are refused (30). Read-only access by omitting the write scopes, and the user's own base role still applies. Automations created through MCP stay off until a person turns them on. No server-side approval for record or table deletes was found (15). Records can hold text written by others, and the only guidance found is a line advising users to trust the tools and data sources they connect (3). Record revision history names the authorising user and the OAuth app or token. The audit log API keeps 180 days and is limited to Enterprise Scale (11). HackerOne bug bounty, SOC 2 Type 2, ISO 27001 and 27701. security.txt has no Expires field (19). 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. ## 6. Reliability, 94 out of 100, up to 1.2 more on the total Why it scored 94: Graded on the REST Web API and the hosted MCP server. Statuspage at status.airtable.com with one component and incident history (20). No incident in the 90 days to 8 October 2026. The latest, a major outage of 1 hour 42 minutes on 8 July 2026, falls two days outside the window (30). 5 requests a second per base, 50 a second per user across personal access tokens, and monthly caps of 1,000 calls on Free and 100,000 on Team. No separate limit for the MCP server was found (13). A 429 means waiting 30 seconds, the docs ask for back-off, 503 may carry Retry-After, and `performUpsert` makes a repeated write safe. No idempotency keys, and no Retry-After documented on 429 (11). A 99.9 per cent uptime SLA is published for Enterprise plans (10). The Web API is generally available and the MCP docs carry no beta label, though the companion CLI is marked experimental (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. ## 7. Transparency & trust, 86 out of 100, up to 1.2 more on the total Made of editorial 72, provenance 100. Why it scored 86: Closed service with published Terms of Service (31 May 2024) and Developer Terms (1 December 2022). The CLI and airtable.js are MIT (15). Privacy policy updated 15 July 2026, a DPA that can be signed online, and AI Terms that rule out model training on customer data. No retention periods for base content were found, and deleted content may stay in backups (20). Deprecation guidelines aim for 12 months' notice on the Web API and list past deprecations with dates, while reserving the right to act without notice (17). Sub-processor list updated 25 August 2026 with countries, plus EU and Australian data residency (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. ## 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 MCP server's tool input schemas and annotations, which need a signed-in account. The tool count of 40 comes from the published tools reference - unchecked: the plan cards on airtable.com/pricing, which load in the browser. Prices come from the page's own FAQ and the help centre's plans overview - unchecked: whether signup for the Free plan asks for a card. We didn't complete a signup - unchecked: reply times on the developer community forum - No OpenAPI description, rate limit for the MCP server or retention period for base content was found in the reviewed documentation - The 8 July 2026 outage (1 hour 42 minutes, marked major) falls two days outside the 90-day window used for the incident record - PyPI downloads are left empty because pyairtable is community-built, with about 1.14 million downloads in the week to 8 October 2026 ## Weaknesses - 5 requests a second per base, and a 429 blocks further requests for 30 seconds - Create, update and delete calls take at most 10 records each - Free plan allows 1,000 API calls a month per workspace and 1,000 records per base - No OpenAPI description was found in the reviewed documentation - The only official client library is airtable.js, last released as v0.12.2 on 16 August 2023 ## 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. - Create a personal access token with only the scopes needed and add each base to it. A token with no base added sees nothing - Stay under 5 requests a second per base. After a 429, wait 30 seconds before the next call - Send writes in batches of 10 records, and use `performUpsert` with `fieldsToMergeOn` so a repeated call updates instead of duplicating - Use table and field IDs, not names, and set `returnFieldsByFieldId` so a rename doesn't break the call - POST to `/listRecords` when a `filterByFormula` would push the URL past 16,000 characters ## 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.