# Fix list: Taskrabbit Partner API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/taskrabbit, the October 2026 research run, assessed 14 October 2026. Grade E, 44.3 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 Taskrabbit Partner API: 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, 5 out of 100, up to 11.9 more on the total Why it scored 5: Read with the hosted rubric. No x402, MPP or L402 (0). No public API price, terms are agreed per partner (0). A sandbox exists for every home services operation, but only after Taskrabbit grants credentials, so partial credit (5 of 20). A person must request access and be approved, and the home services key comes from a partnership manager (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, 39 out of 100, up to 10.7 more on the total Why it scored 39: OAuth 2.0 client credentials with one declared scope and short-lived tokens. The home services overview calls the credential an API key from the partnership manager, and no rotation or scope choice is documented (20 of 30). Separate sandbox and production. Booking requires an explicit flag that the customer accepted Taskrabbit's terms, and cancellation follows the standard refund policy. No read-only credential was found (5 of 20). Responses carry project, address and Tasker details, little free text from outside parties (10 of 15). Every response has a request_id and Svix keeps webhook delivery logs. No API call log for the partner was found (4 of 15). No security.txt (404), disclosure policy, bug bounty or certification was found (0 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. ## 3. Reliability, 52 out of 100, up to 9.6 more on the total Why it scored 52: Read with the hosted lines for the Partner Platform API. status.taskrabbit.com on Statuspage has a Global API component and the websites, with no component for the Partner Platform or Dolly (20). No incident is recorded in the last 90 days, but the newest incident on the page dates from December 2019, so we read the history as clean but not evidently kept up and scored 20 rather than 30. No rate limits with numbers were found (0). No 429 or backoff guidance. Bids and v2 orders are documented as idempotent (7). No SLA was found (0). The Delivery API is in production, but the Getting Started page still says the home services API is under development and not ready for public use, while its guides say sandbox and production (5). 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, 46 out of 100, up to 8.8 more on the total Why it scored 46: No field selection, and list projects has no limit parameter (8 of 25). List projects filters by status and brand and sorts by created_at, with no pagination (8 of 20). A common error envelope carries a code, a message, an error uuid and a request_id, but no catalogue of codes was found (12 of 20). Bids are idempotent, v2 orders and quotes return the existing record on a repeat, and webhooks are signed and retried by Svix (14 of 20). No official SDK. A Postman collection comes from the business development contact, base URLs differ per partner and booking needs five required fields (4 of 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. Maintenance & community, 35 out of 100, up to 5.7 more on the total Why it scored 35: Closed service. The hub's page records show the Partner Public API ep-v2 reference added on 14 September 2026, 30 days before this check (30). No other dated change in the last 90 days was found, and there is no changelog (0). Support is through the partnerships contact and an access form, with a stated review time of two business days, a vendor claim we did not test. No public changelog or community channel (5 of 15). No official SDKs (0 of 15). No published packages to assess (0 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. ## 6. Schema & documentation, 67 out of 100, up to 5.4 more on the total Why it scored 67: Every reference page embeds an OpenAPI 3.1 definition for its operation with request and response schemas. No single downloadable specification was found (15 of 25). llms.txt indexes Markdown copies of all 51 guide and reference pages (10). Guides state each call's purpose and order, and when it is optional (an estimate is not required before a bid) (13 of 20). Required fields, uuid and integer formats and status filters are typed, with examples (11 of 15). Every operation has request and response examples. The Partner Platform documents only 400 responses, ep-v2 documents seven error codes (11 of 15). The version 2025-12 is in the URL. No public changelog was found, and /changelog returns 404 (7 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. ## 7. Transparency & trust, 57 out of 100, up to 3.8 more on the total Made of editorial 34, provenance 79. Why it scored 57: Closed service. Consumer terms (25 July 2026) are published, and the partner agreement that governs the API is not (12 of 30). The privacy policy (26 May 2026) names the controller and entities, gives US storage and the Data Privacy Framework, but no retention periods, and no DPA was found (15 of 30). No deprecation policy or dated notices were found (0 of 20). Service-provider categories and the US data location are stated, with no named sub-processor list (7 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): - Terms of service: read, states 6 of the 7 things a reader expects (9.1 of 10) - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## 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: which countries and services the Partner Platform covers. The OpenAPI examples use en-US and USD, and taskrabbit.com redirected our reader to /browser/unsupported - Whether the home services API is generally available. The Getting Started page says under development, the home services guides say sandbox and production - Whether the home services credential is an API key or an OAuth client, since the overview and the OpenAPI definition disagree - No rate limits, SLA or changelog were found in the developer hub ## Weaknesses - No self-serve access. Credentials come from Taskrabbit after a reviewed request or from a partnership manager - No public API price. Commercial terms are agreed per partner - No rate limits, 429 guidance, SLA or changelog found in the developer hub - The Getting Started page still says the home services API is under development and not ready for public use - No security.txt, bug bounty or certification found ## 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. - Ask the partnership manager for the partner subdomain, token URL and brand_uuid before the first call. Base URLs are https://.partner-platform.taskrabbit.com/2025-12 - Call bid before book. A bid holds the price and time window for a few minutes only - Send client_accepted_taskrabbit_policy only after the customer has agreed to Taskrabbit's terms, because booking requires it - Regenerate OAuth client-credentials tokens on a schedule. The docs say they expire frequently - Verify the Svix signature on every webhook and make the handler idempotent, as the docs ask ## 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.