{
  "fixes": {
    "slug": "hubspot-mcp",
    "name": "HubSpot API + MCP",
    "listing": "https://www.anchorterminal.com/tools/hubspot-mcp",
    "markdown": "# Fix list: HubSpot API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/hubspot-mcp, the October 2026 research run, assessed 1 October 2026. Grade BB, 71.6 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 HubSpot API + MCP: 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, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0). Plan prices public, Starter $7 a seat a month yearly or $20 monthly, Professional $90 or $100 plus $1,500 onboarding, Enterprise $150 plus $3,500, with extra HubSpot Credits at $0.010 each. API calls themselves aren't priced (10). Free CRM for up to 2 users with no card, and the API and remote MCP work on it (20). A person signs up in a browser and creates the MCP connector or app (0).\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. Reliability, 60 out of 100, up to 8 more on the total\n\nWhy it scored 60: Status page at status.hubspot.com with component history (20). Twelve entries since 3 July 2026, several over an hour on core platform services, among them EU customer platform tools impaired for 3 h 9 min on 22 July, event ingestion delayed 5 hours on 28 July, workflow actions delayed 5 h 45 min on 21 August and the Salesforce integration down about 8 hours on 24 September. None names the public API or the MCP server, which is why this isn't 0 (5). Limits published per app type and tier, 100 to 190 requests per 10 seconds and 250,000 to 1,000,000 a day for private apps, 110 per 10 seconds for public apps (15). 429s carry `errorType` RATE_LIMIT and `policyName`, and responses carry `X-HubSpot-RateLimit-*` headers, but the usage page gives no Retry-After or backoff guidance and we found no idempotency keys for CRM writes (10 of 15). No SLA found in what we read (0). Remote MCP server GA since 13 April 2026, though about ten tools for revenue objects and quotes are beta (10).\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## 3. Agent ergonomics, 72 out of 100, up to 4.6 more on the total\n\nWhy it scored 72: 32 MCP tools (5), with scopes trimmed to the tools and permissions the user grants at install, and `discover_hubspot_schema` and `tool_guidance` to fetch context on demand (3 more, 8 of 25). Search takes filter groups, sorts, a 200-record page and a `properties` list, and REST reads select properties (20). Errors carry a category and a correlation ID (16 of 20). `manage_crm_objects` shows a proposed-changes summary and needs the user's confirmation before any create or update, and there's no delete tool. We found no `readOnlyHint` or `destructiveHint` documented and no idempotency keys (13 of 20). Official SDKs for Node (14.0.1, 1 July 2026), Python, PHP and Ruby (15).\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## 4. Security \u0026 auth, 82 out of 100, up to 3.2 more on the total\n\nWhy it scored 82: The remote MCP server takes only OAuth 2.1 with PKCE, with scopes set by the tools and the user's grant. REST uses OAuth apps or Service Keys, which are scoped and rotate with a 7-day grace period (30). Writes need explicit user confirmation after a proposed-changes summary, MCP has no delete tools, and turning on Sensitive Data blocks calls, emails, meetings, notes and tasks from the MCP server. No documented read-only mode (17 of 20). The server reads emails, conversations and notes written by outsiders, and we found no injection guidance beyond the Sensitive Data switch (5 of 15). Account activity history can be viewed and exported per the trust centre. Nothing MCP-specific is documented (10 of 15). PGP-signed security.txt valid until 2034, a HackerOne bug bounty, SOC 1 Type II, SOC 2 Type II and SOC 3 (20).\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## 5. Maintenance \u0026 community, 84 out of 100, up to 1.4 more on the total\n\nWhy it scored 84: Developer Platform 2026.09 and a changelog post on 15 September 2026 (30). Changelog posts on 11 August, 14 August, 27 August, 8 September and 15 September 2026 (20). Public changelog and developer community. We didn't check forum response times (12 of 15). Not in the official MCP registry under a HubSpot namespace, only third-party servers, but official SDKs are current (15). The Node SDK has test and lint CI and moved to Node 22 in 14.0.0, but still wraps the v3 APIs that lose support in September 2027 (7 of 10).\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## 6. Schema \u0026 documentation, 92 out of 100, up to 1.3 more on the total\n\nWhy it scored 92: OpenAPI specs in the public HubSpot-public-api-spec-collection repository (25). llms.txt on developers.hubspot.com (10). MCP tool docs explain each tool, give search limits (five filter groups of six filters, 200 results a page), and the server has a `tool_guidance` tool the model can call (16 of 20). Typed inputs with operator enums in search (13 of 15). Examples and a standard error body with `status`, `message`, `correlationId` and `category` (13 of 15). Date-based API versions (2026-03, 2026-09) and a dated developer changelog with breaking-change and sunset posts (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## 7. Transparency \u0026 trust, 86 out of 100, up to 1.2 more on the total\n\nMade of editorial 71, provenance 100.\n\nWhy it scored 86: Closed service with terms naming HubSpot, Inc. (15). Privacy policy updated 16 September 2026 with a DPA whose Annex 3 lists subprocessors. Retention reads 'a reasonable period', and the policy says HubSpot may process personal data to train its AI models (18 of 30). Dated sunsets, Pipelines v1 on 4 December 2026 (announced 14 August) and v1 to v3 APIs and legacy apps in September 2027 (announced 15 September 2026), plus date-based API versions (20). Subprocessor page and regional data centres disclosed (18 of 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\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- Whether the MCP tools set readOnlyHint or destructiveHint in tools/list, not documented\n- Whether any HubSpot tier carries an uptime SLA, not found in the pages we read\n- Whether MCP calls spend HubSpot Credits\n\n## Weaknesses\n\n- Several incidents over an hour in the 90 days to 1 October 2026, up to about 8 hours\n- Emails, notes and conversations reach the model with no injection guidance\n- Privacy policy allows using personal data to train HubSpot AI models\n- No Retry-After documented on 429s and no idempotency keys for CRM writes\n- Some tools need Marketing Hub or Revenue Hub Professional, and about ten are beta\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- Call `discover_hubspot_schema` before writing, so property names match the portal\n- Use `search_crm_objects` with filter groups and a `properties` list instead of listing everything\n- Expect `manage_crm_objects` to stop for user confirmation, so plan the turn around it\n- Read `policyName` on a 429 to tell a 10-second burst from the daily cap\n- Ask for Sensitive Data to stay off only if the job needs calls, emails or notes, since it blocks them\n\n## What the review panel asked for\n\n- document tool annotations\n- add idempotency keys\n- an AI training opt-out\n- an MCP call log\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": 71.6,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0). Plan prices public, Starter $7 a seat a month yearly or $20 monthly, Professional $90 or $100 plus $1,500 onboarding, Enterprise $150 plus $3,500, with extra HubSpot Credits at $0.010 each. API calls themselves aren't priced (10). Free CRM for up to 2 users with no card, and the API and remote MCP work on it (20). A person signs up in a browser and creates the MCP connector or app (0).",
        "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": "reliability",
        "name": "Reliability",
        "score": 60,
        "maxGain": 8,
        "reason": "Status page at status.hubspot.com with component history (20). Twelve entries since 3 July 2026, several over an hour on core platform services, among them EU customer platform tools impaired for 3 h 9 min on 22 July, event ingestion delayed 5 hours on 28 July, workflow actions delayed 5 h 45 min on 21 August and the Salesforce integration down about 8 hours on 24 September. None names the public API or the MCP server, which is why this isn't 0 (5). Limits published per app type and tier, 100 to 190 requests per 10 seconds and 250,000 to 1,000,000 a day for private apps, 110 per 10 seconds for public apps (15). 429s carry `errorType` RATE_LIMIT and `policyName`, and responses carry `X-HubSpot-RateLimit-*` headers, but the usage page gives no Retry-After or backoff guidance and we found no idempotency keys for CRM writes (10 of 15). No SLA found in what we read (0). Remote MCP server GA since 13 April 2026, though about ten tools for revenue objects and quotes are beta (10).",
        "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": 72,
        "maxGain": 4.6,
        "reason": "32 MCP tools (5), with scopes trimmed to the tools and permissions the user grants at install, and `discover_hubspot_schema` and `tool_guidance` to fetch context on demand (3 more, 8 of 25). Search takes filter groups, sorts, a 200-record page and a `properties` list, and REST reads select properties (20). Errors carry a category and a correlation ID (16 of 20). `manage_crm_objects` shows a proposed-changes summary and needs the user's confirmation before any create or update, and there's no delete tool. We found no `readOnlyHint` or `destructiveHint` documented and no idempotency keys (13 of 20). Official SDKs for Node (14.0.1, 1 July 2026), Python, PHP and Ruby (15).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 82,
        "maxGain": 3.2,
        "reason": "The remote MCP server takes only OAuth 2.1 with PKCE, with scopes set by the tools and the user's grant. REST uses OAuth apps or Service Keys, which are scoped and rotate with a 7-day grace period (30). Writes need explicit user confirmation after a proposed-changes summary, MCP has no delete tools, and turning on Sensitive Data blocks calls, emails, meetings, notes and tasks from the MCP server. No documented read-only mode (17 of 20). The server reads emails, conversations and notes written by outsiders, and we found no injection guidance beyond the Sensitive Data switch (5 of 15). Account activity history can be viewed and exported per the trust centre. Nothing MCP-specific is documented (10 of 15). PGP-signed security.txt valid until 2034, a HackerOne bug bounty, SOC 1 Type II, SOC 2 Type II and SOC 3 (20).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 84,
        "maxGain": 1.4,
        "reason": "Developer Platform 2026.09 and a changelog post on 15 September 2026 (30). Changelog posts on 11 August, 14 August, 27 August, 8 September and 15 September 2026 (20). Public changelog and developer community. We didn't check forum response times (12 of 15). Not in the official MCP registry under a HubSpot namespace, only third-party servers, but official SDKs are current (15). The Node SDK has test and lint CI and moved to Node 22 in 14.0.0, but still wraps the v3 APIs that lose support in September 2027 (7 of 10).",
        "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"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 92,
        "maxGain": 1.3,
        "reason": "OpenAPI specs in the public HubSpot-public-api-spec-collection repository (25). llms.txt on developers.hubspot.com (10). MCP tool docs explain each tool, give search limits (five filter groups of six filters, 200 results a page), and the server has a `tool_guidance` tool the model can call (16 of 20). Typed inputs with operator enums in search (13 of 15). Examples and a standard error body with `status`, `message`, `correlationId` and `category` (13 of 15). Date-based API versions (2026-03, 2026-09) and a dated developer changelog with breaking-change and sunset posts (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": 86,
        "maxGain": 1.2,
        "reason": "Closed service with terms naming HubSpot, Inc. (15). Privacy policy updated 16 September 2026 with a DPA whose Annex 3 lists subprocessors. Retention reads 'a reasonable period', and the policy says HubSpot may process personal data to train its AI models (18 of 30). Dated sunsets, Pipelines v1 on 4 December 2026 (announced 14 August) and v1 to v3 APIs and legacy apps in September 2027 (announced 15 September 2026), plus date-based API versions (20). Subprocessor page and regional data centres disclosed (18 of 20).",
        "blend": "editorial 71, provenance 100",
        "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"
      }
    ],
    "unchecked": [
      "Whether the MCP tools set readOnlyHint or destructiveHint in tools/list, not documented",
      "Whether any HubSpot tier carries an uptime SLA, not found in the pages we read",
      "Whether MCP calls spend HubSpot Credits"
    ],
    "weaknesses": [
      "Several incidents over an hour in the 90 days to 1 October 2026, up to about 8 hours",
      "Emails, notes and conversations reach the model with no injection guidance",
      "Privacy policy allows using personal data to train HubSpot AI models",
      "No Retry-After documented on 429s and no idempotency keys for CRM writes",
      "Some tools need Marketing Hub or Revenue Hub Professional, and about ten are beta"
    ],
    "agentNotes": [
      "Call `discover_hubspot_schema` before writing, so property names match the portal",
      "Use `search_crm_objects` with filter groups and a `properties` list instead of listing everything",
      "Expect `manage_crm_objects` to stop for user confirmation, so plan the turn around it",
      "Read `policyName` on a 429 to tell a 10-second burst from the daily cap",
      "Ask for Sensitive Data to stay off only if the job needs calls, emails or notes, since it blocks them"
    ],
    "requests": [
      {
        "text": "document tool annotations",
        "reviews": 1
      },
      {
        "text": "add idempotency keys",
        "reviews": 1
      },
      {
        "text": "an AI training opt-out",
        "reviews": 1
      },
      {
        "text": "an MCP call log",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}