{
  "fixes": {
    "slug": "monday",
    "name": "monday.com",
    "listing": "https://www.anchorterminal.com/tools/monday",
    "markdown": "# Fix list: monday.com\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/monday, the October 2026 research run, assessed 8 October 2026. Grade BB, 76.4 out of 100.\n\nThis 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.\n\nFor a coding agent working on monday.com: 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.\n\n## 1. Payments \u0026 pricing, 50 out of 100, up to 6.3 more on the total\n\nWhy it scored 50: No x402, MPP or L402 found (0). Plan prices are public per seat, with daily API call allowances per plan and no per-call price. Extra calls can be bought, with no price shown (10). A Free plan and a free developer sandbox account, with no card needed per the pricing page (20). A documented signup API at signup-logic.monday.com returns an account and an API token after a captcha written for agents, with no browser step. We requested a challenge and it answered, and we didn't create an account (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 2. Security \u0026 auth, 70 out of 100, up to 5.3 more on the total\n\nWhy it scored 70: OAuth 2.1 with PKCE, expiring access tokens, refresh tokens and revocation, 21 scopes, and dynamic client registration on the MCP server. Personal tokens are unscoped and carry every permission their user has, and legacy OAuth tokens don't expire (26). A custom OAuth app can limit the MCP connection to scopes such as `boards:read`, admins can limit MCP to chosen workspaces, and the local server has `--read-only`. No server-side confirmation for deletes was found (14). The MCP security page places prompt-injection defence on the client, and the vendor's agent skill file tells agents to treat board content as data (8). Board activity logs are available through the API. The audit log API is limited to Enterprise admins, and the MCP security page says self-service export of detailed MCP or API audit logs isn't available (7). SOC 2 Type II and ISO 27001:2022 among ten listed attestations, and a vulnerability report form. No security.txt or bug bounty was found (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 3. Reliability, 79 out of 100, up to 4.2 more on the total\n\nWhy it scored 79: Graded on the GraphQL API and the hosted MCP server. Statuspage at status.monday.com with components by region, an API component among them, and incident history (20). In the 90 days to 8 October 2026 it lists a critical platform connectivity incident of 2 hours 8 minutes on 5 September, a major platform latency incident of 2 hours 57 minutes on 13 July, a major automations incident of 32 minutes in the EU on 17 September and three minor ones. None names the API component, and we read the record as one outage plus one long slowdown (10). Daily, per-minute, concurrency, complexity and IP limits are published with numbers per plan (15). 429 carries `Retry-After`, rate limit errors carry `retry_in_seconds`, every response has `RateLimit` headers, and mutations accept an `Idempotency-Key` header (15). A 99.9 per cent uptime SLA is published for the Enterprise plan (10). The API is generally available and the hosted MCP docs carry no beta label, though the tools reference says some newer tools run against a preview API schema (9).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 4. Agent ergonomics, 82 out of 100, up to 2.9 more on the total\n\nWhy it scored 82: The MCP reference lists 64 tools (5 of 25). The local server adds a read-only flag, tool modes and a three-tool dynamic mode, a custom OAuth app can cap the hosted connection by scope, and GraphQL field selection sizes every API response, so 16 overall. Cursor pagination up to 500 items a page, rule-based filters through `query_params`, and lookup by column value (20). Errors carry a code, a status code, a `request_id` and `retry_in_seconds` where it applies, though application errors arrive with HTTP 200 (18). `Idempotency-Key` on mutations with a 30-minute replay window, and readOnlyHint, destructiveHint and idempotentHint on the tools in the source (20). Few required arguments, but an agent must read a board's columns before writing values, and the only official API SDK is for JavaScript and TypeScript (8).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 5. Schema \u0026 documentation, 88 out of 100, up to 2 more on the total\n\nWhy it scored 88: The full GraphQL schema is public as SDL and JSON, with a copy per API version, and the MCP tools are typed with Zod schemas in the open-source toolkit (25). llms.txt files at monday.com and developer.monday.com/api-reference, with a Markdown copy of each docs page (10). The tools reference has a page per tool for 64 tools and the schema carries descriptions. Some tool descriptions in the source are one line, such as \"Delete an item\", and the vendor's agent skill file names 2024-10 as the latest stable version and gives a Free daily limit of 200, both at odds with the docs (14). GraphQL inputs are typed with enums and required flags, but column values are passed as a JSON string whose shape depends on the column type (10). Curl and GraphQL examples throughout, and an error page that lists codes by status with sample bodies (14). Dated quarterly versions with release notes that separate breaking changes, plus a changelog (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## 6. Transparency \u0026 trust, 80 out of 100, up to 1.8 more on the total\n\nMade of editorial 73, provenance 86.\n\nWhy it scored 80: Closed service with published Terms of Service (5 May 2026) and Developer Terms. The MCP server, toolkit and API SDK are MIT (15). Privacy policy updated 1 October 2026, a DPA dated 20 December 2023 with deletion or return of data after termination, and an AI trust centre that rules out model training on customer input and output. Retention is stated as for as long as reasonably needed, with no period given (20). API versions are deprecated with at least six months' notice and listed with dates. SSE on the hosted MCP server is called deprecated and unsupported with no date given (18). Sub-processor list updated 24 June 2026 with hosting regions, and US, EU and APAC account regions (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Terms of service: read, states 7 of the 7 things a reader expects, and has 2 clauses that cost points (6 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Maintenance \u0026 community, 85 out of 100, up to 1.3 more on the total\n\nWhy it scored 85: @mondaydotcomorg/agent-toolkit 5.72.0 was published on 7 October 2026, @mondaydotcomorg/api 14.1.0 on 6 October, and API version 2026-10 became current on 1 October per the version table (30). 44 toolkit releases on npm between 10 July and 7 October 2026 (20). A public changelog, release notes and a developer community forum. We couldn't read the GitHub issue tracker or reply times, so this line is scored conservatively (12). Listed in the official MCP registry as com.monday/monday.com, though the entry is version 0.0.1 from 23 October 2025 and still lists the SSE remote, and the API SDK is current (15). The MCP repository runs lint, build and tests on pull requests and has 78 test files. Git tags stop at v0.0.163 on 14 April 2026 while npm releases continue (8).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## What we couldn't check\n\nWhat 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.\n\n- unchecked: US dollar prices. monday.com/pricing served our reader in pounds, so `unitPrices` is left empty\n- unchecked: GitHub stars, open issues and reply times for mondaycom/mcp. The GitHub API refused us for its rate limit\n- unchecked: the hosted MCP server's live tool list, input schemas and annotations, which need a signed-in account. The count of 64 comes from the published tools reference, and annotations were read in the open-source toolkit\n- unchecked: which plan and limits an account created through the agent signup API receives. We requested a captcha challenge, which answered, and didn't create an account\n- unchecked: whether Free plan signup in a browser asks for a card. The pricing page says no card is needed\n- The agent skill file gives a Free plan daily limit of 200 calls, while the rate limits page and the pricing page give 1,000 for Free, Basic and Standard. We used the docs' figure\n- The docs call SSE on the hosted MCP server deprecated and unsupported, while the MCP registry entry and the agent skill file still list https://mcp.monday.com/sse, which answered our request with a 302. No removal date was found\n- The status incident of 5 September 2026 is titled as planned maintenance for 5 August but its updates describe connectivity issues across the platform, and it is marked critical\n- No bug bounty, security.txt, retention period for account content or price for extra API calls was found in the reviewed pages\n\n## Weaknesses\n\n- Personal API tokens have no scopes. Each carries every permission its user has in the app\n- 1,000 API calls a day on Free, Basic and Standard, shared with MCP tool calls, against 10,000 on Pro and 25,000 on Enterprise\n- status.monday.com lists a critical platform incident of 2 hours 8 minutes on 5 September 2026 and a major latency incident of 2 hours 57 minutes on 13 July 2026\n- The MCP security page says self-service export of detailed MCP or API audit logs isn't available, and the audit log API is limited to Enterprise admins\n- Column values travel as a JSON string whose shape depends on the column type, and the only official API SDK is for JavaScript and TypeScript\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Send an `API-Version` header such as 2026-10 on every call. Without it the API uses whichever version is current\n- Read the board's columns first (`get_board_info` or `boards { columns }`), then write column values as a JSON string keyed by column ID\n- Reuse one `Idempotency-Key` per mutation when retrying after a timeout or 5xx. After a 429, wait for `Retry-After` or `retry_in_seconds`\n- Page items with `items_page` and `next_items_page`, at most 500 a page. Cursors expire after 60 minutes\n- For a narrower grant than a personal token, connect MCP through a custom OAuth app with only scopes such as `boards:read`\n\n## When it's done\n\nSend 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.\n",
    "grade": "BB",
    "score": 76.4,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 50,
        "maxGain": 6.3,
        "reason": "No x402, MPP or L402 found (0). Plan prices are public per seat, with daily API call allowances per plan and no per-call price. Extra calls can be bought, with no price shown (10). A Free plan and a free developer sandbox account, with no card needed per the pricing page (20). A documented signup API at signup-logic.monday.com returns an account and an API token after a captcha written for agents, with no browser step. We requested a challenge and it answered, and we didn't create an account (20).",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 70,
        "maxGain": 5.3,
        "reason": "OAuth 2.1 with PKCE, expiring access tokens, refresh tokens and revocation, 21 scopes, and dynamic client registration on the MCP server. Personal tokens are unscoped and carry every permission their user has, and legacy OAuth tokens don't expire (26). A custom OAuth app can limit the MCP connection to scopes such as `boards:read`, admins can limit MCP to chosen workspaces, and the local server has `--read-only`. No server-side confirmation for deletes was found (14). The MCP security page places prompt-injection defence on the client, and the vendor's agent skill file tells agents to treat board content as data (8). Board activity logs are available through the API. The audit log API is limited to Enterprise admins, and the MCP security page says self-service export of detailed MCP or API audit logs isn't available (7). SOC 2 Type II and ISO 27001:2022 among ten listed attestations, and a vulnerability report form. No security.txt or bug bounty was found (15).",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 79,
        "maxGain": 4.2,
        "reason": "Graded on the GraphQL API and the hosted MCP server. Statuspage at status.monday.com with components by region, an API component among them, and incident history (20). In the 90 days to 8 October 2026 it lists a critical platform connectivity incident of 2 hours 8 minutes on 5 September, a major platform latency incident of 2 hours 57 minutes on 13 July, a major automations incident of 32 minutes in the EU on 17 September and three minor ones. None names the API component, and we read the record as one outage plus one long slowdown (10). Daily, per-minute, concurrency, complexity and IP limits are published with numbers per plan (15). 429 carries `Retry-After`, rate limit errors carry `retry_in_seconds`, every response has `RateLimit` headers, and mutations accept an `Idempotency-Key` header (15). A 99.9 per cent uptime SLA is published for the Enterprise plan (10). The API is generally available and the hosted MCP docs carry no beta label, though the tools reference says some newer tools run against a preview API schema (9).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 82,
        "maxGain": 2.9,
        "reason": "The MCP reference lists 64 tools (5 of 25). The local server adds a read-only flag, tool modes and a three-tool dynamic mode, a custom OAuth app can cap the hosted connection by scope, and GraphQL field selection sizes every API response, so 16 overall. Cursor pagination up to 500 items a page, rule-based filters through `query_params`, and lookup by column value (20). Errors carry a code, a status code, a `request_id` and `retry_in_seconds` where it applies, though application errors arrive with HTTP 200 (18). `Idempotency-Key` on mutations with a 30-minute replay window, and readOnlyHint, destructiveHint and idempotentHint on the tools in the source (20). Few required arguments, but an agent must read a board's columns before writing values, and the only official API SDK is for JavaScript and TypeScript (8).",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 88,
        "maxGain": 2,
        "reason": "The full GraphQL schema is public as SDL and JSON, with a copy per API version, and the MCP tools are typed with Zod schemas in the open-source toolkit (25). llms.txt files at monday.com and developer.monday.com/api-reference, with a Markdown copy of each docs page (10). The tools reference has a page per tool for 64 tools and the schema carries descriptions. Some tool descriptions in the source are one line, such as \"Delete an item\", and the vendor's agent skill file names 2024-10 as the latest stable version and gives a Free daily limit of 200, both at odds with the docs (14). GraphQL inputs are typed with enums and required flags, but column values are passed as a JSON string whose shape depends on the column type (10). Curl and GraphQL examples throughout, and an error page that lists codes by status with sample bodies (14). Dated quarterly versions with release notes that separate breaking changes, plus a changelog (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 80,
        "maxGain": 1.8,
        "reason": "Closed service with published Terms of Service (5 May 2026) and Developer Terms. The MCP server, toolkit and API SDK are MIT (15). Privacy policy updated 1 October 2026, a DPA dated 20 December 2023 with deletion or return of data after termination, and an AI trust centre that rules out model training on customer input and output. Retention is stated as for as long as reasonably needed, with no period given (20). API versions are deprecated with at least six months' notice and listed with dates. SSE on the hosted MCP server is called deprecated and unsupported with no date given (18). Sub-processor list updated 24 June 2026 with hosting regions, and US, EU and APAC account regions (20).",
        "blend": "editorial 73, provenance 86",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 85,
        "maxGain": 1.3,
        "reason": "@mondaydotcomorg/agent-toolkit 5.72.0 was published on 7 October 2026, @mondaydotcomorg/api 14.1.0 on 6 October, and API version 2026-10 became current on 1 October per the version table (30). 44 toolkit releases on npm between 10 July and 7 October 2026 (20). A public changelog, release notes and a developer community forum. We couldn't read the GitHub issue tracker or reply times, so this line is scored conservatively (12). Listed in the official MCP registry as com.monday/monday.com, though the entry is version 0.0.1 from 23 October 2025 and still lists the SSE remote, and the API SDK is current (15). The MCP repository runs lint, build and tests on pull requests and has 78 test files. Git tags stop at v0.0.163 on 14 April 2026 while npm releases continue (8).",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "read, states 7 of the 7 things a reader expects, and has 2 clauses that cost points",
        "points": 6,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: US dollar prices. monday.com/pricing served our reader in pounds, so `unitPrices` is left empty",
      "unchecked: GitHub stars, open issues and reply times for mondaycom/mcp. The GitHub API refused us for its rate limit",
      "unchecked: the hosted MCP server's live tool list, input schemas and annotations, which need a signed-in account. The count of 64 comes from the published tools reference, and annotations were read in the open-source toolkit",
      "unchecked: which plan and limits an account created through the agent signup API receives. We requested a captcha challenge, which answered, and didn't create an account",
      "unchecked: whether Free plan signup in a browser asks for a card. The pricing page says no card is needed",
      "The agent skill file gives a Free plan daily limit of 200 calls, while the rate limits page and the pricing page give 1,000 for Free, Basic and Standard. We used the docs' figure",
      "The docs call SSE on the hosted MCP server deprecated and unsupported, while the MCP registry entry and the agent skill file still list https://mcp.monday.com/sse, which answered our request with a 302. No removal date was found",
      "The status incident of 5 September 2026 is titled as planned maintenance for 5 August but its updates describe connectivity issues across the platform, and it is marked critical",
      "No bug bounty, security.txt, retention period for account content or price for extra API calls was found in the reviewed pages"
    ],
    "weaknesses": [
      "Personal API tokens have no scopes. Each carries every permission its user has in the app",
      "1,000 API calls a day on Free, Basic and Standard, shared with MCP tool calls, against 10,000 on Pro and 25,000 on Enterprise",
      "status.monday.com lists a critical platform incident of 2 hours 8 minutes on 5 September 2026 and a major latency incident of 2 hours 57 minutes on 13 July 2026",
      "The MCP security page says self-service export of detailed MCP or API audit logs isn't available, and the audit log API is limited to Enterprise admins",
      "Column values travel as a JSON string whose shape depends on the column type, and the only official API SDK is for JavaScript and TypeScript"
    ],
    "agentNotes": [
      "Send an `API-Version` header such as 2026-10 on every call. Without it the API uses whichever version is current",
      "Read the board's columns first (`get_board_info` or `boards { columns }`), then write column values as a JSON string keyed by column ID",
      "Reuse one `Idempotency-Key` per mutation when retrying after a timeout or 5xx. After a 429, wait for `Retry-After` or `retry_in_seconds`",
      "Page items with `items_page` and `next_items_page`, at most 500 a page. Cursors expire after 60 minutes",
      "For a narrower grant than a personal token, connect MCP through a custom OAuth app with only scopes such as `boards:read`"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}