# Fix list: Pipedrive API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/pipedrive, the October 2026 research run, assessed 1 October 2026. Grade C, 60.6 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 Pipedrive 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. ## 1. Reliability, 53 out of 100, up to 9.4 more on the total Why it scored 53: Status page at status.pipedrive.com (run on Sorry) with dozens of components, including REST API v1 but nothing for API v2 or the MCP server (20). In the 90 days to 1 October 2026 it logged a services incident on 22 September that took down 17 services for 2 h 9 min, a Nova outage of 1 h 8 min on 18 September, email integration down from 4 to 8 September and invoice integration down for 9 h 56 min on 1 to 2 September (5). Rate limits documented in detail, a daily token budget per company plus burst limits per 2 seconds by plan and auth type (15). Responses carry `x-ratelimit-*` and `x-daily-requests-left` headers and a 429 when the budget runs out, but we found no Retry-After or safe-retry guidance for writes (8 of 15). No SLA found (0). REST is GA. The MCP server is labelled BETA in Pipedrive's Claude setup article, though the launch post doesn't say so (5 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). Plan prices public, Lite $14 to Ultimate $79 a seat a month billed yearly, with token top-ups from $100 a month. No per-call price for the API (10). 14-day trial with no card (20). 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. Security & auth, 53 out of 100, up to 8.2 more on the total Why it scored 53: Personal API tokens carry the user's full rights, one active per user per company, and per the 30 September check older docs still show the token as an `api_token` query parameter. OAuth 2.0 with scopes for apps, and the MCP server is OAuth only with scopes for deals, contacts, leads, activities, products and search (25, less 10 for the query-string option, 15 of 30). No read-only mode or write confirmation documented for MCP (7 of 20). Email sync and notes reach the model, and we found no injection guidance (3 of 15). The launch post says every MCP action is recorded in Pipedrive's change logs (12 of 15). ISO 27001:2022, ISO 27701, SOC 2 Type 2 and SOC 3 in the trust centre, with a responsible disclosure programme. No security.txt (404) (16 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 4. Agent ergonomics, 61 out of 100, up to 6.3 more on the total Why it scored 61: No published MCP tool list or count, and Pipedrive's own Claude guide warns the client may not load every tool by default. v2 list endpoints take a limit and a cursor (12 of 25). Cursor pagination and filters on v2 (18 of 20). We didn't check the error format closely (12 of 20). No idempotency keys or tool annotations found (4 of 20). Official SDKs for Node (33.7.0, 8 September 2026) and PHP (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 5. Schema & documentation, 80 out of 100, up to 3.3 more on the total Why it scored 80: OpenAPI file for v2 per the 30 September check (25). llms.txt on the readme.io docs (10). The MCP server's tool list isn't published, so we can't judge its descriptions. API reference descriptions are adequate (10 of 20). Typed parameters in the OpenAPI (12 of 15). Examples on every reference page. We didn't read an error reference (10 of 15). v1 and v2 paths and a dated changelog that flags breaking changes and deprecations (13 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## 6. Transparency & trust, 78 out of 100, up to 1.9 more on the total Made of editorial 66, provenance 90. Why it scored 78: Closed service with terms naming Pipedrive Inc. in the US and Pipedrive OÜ in the EU (15). Privacy notice updated 2 July 2026, with DPF and SCCs and a subprocessor link, but no retention periods after closure and no clear statement on training AI with customer data (18 of 30). Dated deprecations with notice, such as the Channels API (announced 14 November 2025, effective 1 February 2026) and deprecated v1 endpoints out of support from 1 August 2026 (16 of 20). Subprocessor list maintained, including Anthropic and Recall.ai, on AWS in several regions (17 of 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. Provenance checks not met in full (half of this category, computed from checked facts): - security.txt: not found (0 of 10) ## 7. Maintenance & community, 83 out of 100, up to 1.5 more on the total Why it scored 83: Node client v33.7.0 on 8 September 2026 (30). Node releases on 23 July, 6 August, 13 August and twice on 8 September 2026 (20). Public changelog with dated entries, the newest on 1 August 2026. We didn't test support (10 of 15). Not in the official MCP registry (only third-party Pipedrive servers), but official SDKs are current (15). The Node client publishes from CI, and a workflow auto-closes stale issues (8 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - unchecked: status history feed and incidents API, both refused by our fetch rate limit. The incident list comes from the status page's front view - The MCP tool list and count, which Pipedrive doesn't publish - Whether the `api_token` query parameter still works, relying on the 30 September check - Whether the MCP server is still beta, since the Claude setup article says BETA and the launch post doesn't ## Weaknesses - MCP tool list not published, and the server is labelled beta - Four incidents over an hour in September 2026, and no status component for API v2 or MCP - Personal API tokens carry full user rights and can travel as a query parameter - Daily token budget is shared by the whole company - No security.txt and no retention period after account closure ## 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. - Use v2 endpoints, which cost fewer tokens than v1 - Read `x-daily-requests-left` before a bulk run, since a search costs 40 tokens - Send the token in the `x-api-token` header, never as `api_token` in the URL - Keep under 10 search requests per 2 seconds on every plan - Ask the user to load all Pipedrive tools in the client if an expected tool is missing ## What the review panel asked for - publish the MCP tool list - document the error format - published MCP tool list - a read-only MCP scope ## 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.