# Fix list: Pipedream API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/pipedream, the October 2026 research run, assessed 1 October 2026. Grade B, 65.8 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 Pipedream 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. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). Per-unit prices are public. One credit is 30 seconds of compute at 256 MB, extra credits cost $0.012, and end users beyond 100 cost $2 each on Startup (20). Free plan with no card, limited to development (20). A person signs up and creates an OAuth client in the 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. ## 2. Security & auth, 58 out of 100, up to 7.4 more on the total Why it scored 58: OAuth client credentials exchanged for short-lived bearer tokens, short-lived Connect tokens per end user, and OAuth for the end-user MCP server. We found no scopes on client credentials (22). Tools are fenced per app and per external user, and rate-limit tokens cap each user. No read-only mode and no confirmation before writes (10). Actions return third-party content such as email bodies with no prompt-injection guidance found (3). Per-run event history and logs, and no operator audit log found in the docs (8). SOC 2 Type 2 report on request, HIPAA BAA, annual penetration test, security@pipedream.com with a PGP key and a SECURITY.md. No bug bounty and no security.txt (15). 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. ## 3. Reliability, 65 out of 100, up to 7 more on the total Why it scored 65: Atlassian Statuspage at status.pipedream.com with components for the REST and Connect APIs, event sources, workflows, frontends and integrations (20). The history feed shows two incidents in the last 90 days, Connect and HTTP triggers disrupted for about 19 minutes on 28 July 2026 and HTTP triggers down for 28 minutes on 29 July, both under an hour (20). Connect limits published with numbers, 100 token requests a minute per end user, 2,000 account calls and 3,000 tool listings per 5 minutes per project, but none for action runs or tool calls (12). Custom rate-limit tokens (`x-pd-rate-limit`) let you cap each user, but the docs give no status code, Retry-After or backoff advice (3). No SLA found (0). Connect API and MCP server are generally available (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. ## 4. Agent ergonomics, 73 out of 100, up to 4.4 more on the total Why it scored 73: More than 10,000 tools, so 5, plus 10 back because the `x-pd-app-slug` header narrows the server to one app's tools (15). Cursor pagination on list endpoints through the SDKs, and app search by name (15). Tool errors carry `isError` and an origin attribution an agent can act on (15). Since 1 October 2025 every action declares `readOnlyHint`, `destructiveHint` and `openWorldHint`, for example Gmail send-email is a non-destructive, open-world write. No idempotency keys for action runs (15). Official SDKs for TypeScript, Python and Java, but the MCP server needs five headers on every request (13). 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, 74 out of 100, up to 4.2 more on the total Why it scored 74: OpenAPI file at pipedream_openapi_swagger.json per the 30 September check, and every MCP tool carries a JSON Schema built from the component's props (25). llms.txt per the 30 September check (10). Component descriptions state what the action does and link the upstream API docs, rarely when not to use it (12). Props are typed with options and required flags, though custom request actions take free-form JSON (11). Tool failures come back with `isError` and an attribution of where the error came from. Interactive API reference with examples (9). The API is under /v1 and the SDKs follow semver, but the public changelog's last entry is 1 October 2025 (7). 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 65, provenance 90. Why it scored 78: Hosted service under clear terms, with component code under the Pipedream Source Available License, which bars competing commercial use (18). The privacy and security docs state AWS us-east-1 hosting, internal logs deleted within 30 days, customer data kept until you delete it, a subprocessor page and a DPA with SCCs in the terms (24). No deprecation policy, and the terms let Pipedream withdraw anything in Early Access without notice (5). Subprocessors and data location published (18). 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, 79 out of 100, up to 1.8 more on the total Why it scored 79: TypeScript SDK v3.1.6 and Python SDK v2.1.20 released on 2 September 2026, 29 days before this check (30). Four TypeScript SDK releases since 18 August 2026 (20). The public changelog hasn't moved since 1 October 2025, though the components repository took 277 commits in the last 90 days (7). Current official SDKs in TypeScript, Python and Java (15). SDKs are generated with Fern and the components repository has CI, but we didn't confirm test runs (7). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - Whether Workday's purchase has closed, and whether Pipedream pricing or availability will change under Workday - Whether OAuth clients can be limited to read-only or to specific apps - What HTTP status and headers a Connect call gets when it hits a rate limit ## Weaknesses - Public changelog's last entry is 1 October 2025 - Production Connect starts at $150 a month ($99 billed yearly). Free is development only - No published limit or 429 behaviour for action runs and tool calls - No security.txt, no bug bounty and no prompt-injection guidance - Cloud only, in AWS us-east-1 ## 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. - Pass your own user ID as `x-pd-external-user-id` so each user's accounts stay separate - Send `x-pd-app-slug` to load one app's tools rather than 10,000 - Use a Connect rate-limit token (`x-pd-rate-limit`) to cap runaway loops per user - Check `isError` on tool results before treating a call as done - Stay on `x-pd-environment: development` until billing is set, since production needs a paid plan ## What the review panel asked for - changelog for component changes - deprecation policy - scoped OAuth clients - operator audit log ## 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.