# Fix list: Guru From Anchor Terminal's listing at https://www.anchorterminal.com/tools/guru, the October 2026 research run, assessed 3 October 2026. Grade E, 45.3 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 Guru: 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, 0 out of 100, up to 12.5 more on the total Why it scored 0: No x402, MPP or L402 (0). The pricing page shows no prices and sends every visitor to sales (0). No free plan or trial on the pricing or home pages. A blog post from 2020, updated in 2023, describes a free Starter plan for 10 users and points to a pricing page that no longer lists it (0). A person has to buy through sales, then sign in and approve OAuth or create a token (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. Reliability, 48 out of 100, up to 10.4 more on the total Why it scored 48: Read as a hosted service. Atlassian Statuspage at status.getguru.com with components for the web app, extension, Slack bot, API, analytics and infrastructure and an incident history back to 2021, but no MCP component (20). Two incidents in the last 90 days. On 24 July 2026 a third-party network incident caused timeouts and login failures on some cells, resolved at 04:25 PT with no start time given, and on 7 August intermittent connectivity made new MCP registrations fail, resolved 17 minutes after the first update. We couldn't tell whether 24 July ran past an hour, so we scored between the minor and one-major lines (15 of 30). No rate limits with numbers in the developer docs or the MCP help article, and the terms leave AI usage limits to each order (0). No 429 or backoff guidance in the docs. The Python SDK maps 429 to `RateLimitError` without reading Retry-After (3 of 15). The terms sell the service as is and as available with no uptime commitment, and we found no SLA (0). The MCP server is at 1.0.2 in the official registry with no beta label (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. ## 3. Agent ergonomics, 48 out of 100, up to 8.5 more on the total Why it scored 48: We couldn't count the MCP tools without signing in. The developer page lists five, the help centre's 14 actions suggest more, and no toolsets or read-only subset are documented (15). The REST API pages with Link headers and paging tokens, returns at most 50 cards a page, and filters and sorts cards. MCP paging is unknown (14 of 20). Status codes per operation, but no error body format documented (8 of 20). The help centre says the MCP server can create cards, move cards and folders, archive cards, apply draft edits and change collaborators, and we found no annotations, confirmation step or idempotency guidance. The developer page says Update Card suggests changes, which the help centre doesn't repeat (5 of 20). One URL with OAuth for pre-approved clients. The only official SDK is Python, at 0.1.0 on GitHub and not on PyPI (6 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. ## 4. Security & auth, 52 out of 100, up to 8.4 more on the total Why it scored 52: OAuth for MCP clients Guru has pre-approved, while other clients need Guru Support to allowlist them, and no scopes are documented. The REST API takes basic auth with an email and a user token that reads and writes with the user's rights, or a collection token that's read-only and limited to one collection, and the MCP server takes `Bearer email:token`. No secret in a query string (22 of 30). Collection tokens give a read-only key for one collection, and every call keeps the user's Guru permissions. MCP actions include archive and move with no documented confirmation, though the developer page describes card changes as drafts and suggestions (10 of 20). Tools return cards and connected-source documents written by people, and we found no prompt-injection guidance. The security page says ingestion masks PII, PHI and financial data (4 of 15). We found no audit log for API or MCP calls in the docs we read, and analytics cover card usage (5 of 15). The security page lists a SOC 2 Type II report under NDA, PCI SAQ A-EP, Data Privacy Framework certification and penetration tests twice a year. No security.txt, disclosure policy or bug bounty found (11 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. ## 5. Schema & documentation, 58 out of 100, up to 6.8 more on the total Why it scored 58: Guru's own Python SDK repository carries a Swagger 2.0 file for the REST API, 175 paths and 251 operations with basic auth, enums and defaults. The MCP server is closed and its tool schemas aren't published outside a signed-in session (18). llms.txt at developer.getguru.com and a Markdown copy of each docs page (10). The developer site describes five MCP tools in one line each with no when-not-to-use, while the help centre article (updated 19 September 2026) describes 14 actions in five groups without tool names (6 of 20). The REST spec has enums for query type, sort field and sort order and a 50-result default, with free strings elsewhere. MCP inputs weren't visible to us (8 of 15). One curl example in the quick start, status codes 400, 401, 403, 404 and 412 in the spec, and no error catalogue (8 of 15). A v1 path, a developer changelog with four undated entries, and monthly release notes in the help centre that stop at April 2026 (8 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. Maintenance & community, 46 out of 100, up to 4.7 more on the total Why it scored 46: Guru's SDK refreshed its vendored API spec on 30 July 2026 to match server-side parameter renames, the most recent dated API change we found (20). The help centre's release notes stop at April 2026 and the developer changelog is undated, so we found fewer than three dated entries in the last 90 days (0). A closed service with a help centre and a community site, while the developer changelog is stale and the MCP repository holds only a README and server.json (6 of 15). Registered as com.getguru/mcp-server 1.0.2 in the official MCP registry under Guru's own domain namespace (15). The Python SDK runs CircleCI and takes Dependabot updates, but it isn't published to PyPI (5 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. ## 7. Transparency & trust, 61 out of 100, up to 3.4 more on the total Made of editorial 47, provenance 75. Why it scored 61: A closed service under terms dated 25 March 2026. The SDK is MIT, and the MCP repository holds only a README and server.json (15). The terms delete content 90 days after a subscription ends and bar training publicly available models on customer content, while allowing models private to that customer. The security page says third-party LLMs neither train on nor retain customer data. The privacy policy (modified 19 August 2025) gives no retention periods and names no processors (16 of 30). The terms promise 30 days' email notice of material changes, and the January 2026 release notes record the /boards endpoint's sunset, but there's no API deprecation policy (10 of 20). The security page says Guru runs on AWS and the privacy policy says EU personal data goes to the United States, but we found no subprocessor list (6 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): - Domain age: getguru.com, no registry record we could read (0 of 15) - 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: the MCP server's tool names, input schemas and annotations, which aren't published outside a signed-in session. The developer site lists five tools and the help centre 14 actions. - unchecked: whether the 24 July 2026 incident ran over an hour. The feed gives only the resolution time. - unchecked: the OAuth2 clients and impersonation token pages in the developer docs, and whether OAuth scopes exist. - unchecked: an audit log for API or MCP calls, which we didn't find in the docs we read. - unchecked: subprocessor list and DPA, which we didn't find linked from the security or privacy pages. - unchecked: the registration date of getguru.com. - Whether a free plan or trial exists at sign-up. The pricing page shows none, and a 2020 blog post describes a free Starter plan. ## Weaknesses - No public prices, plans or trial, and the pricing page sends everyone to sales - No rate limits, 429 guidance or SLA published, and the terms sell the service as is - The developer site lists five MCP tools while the help centre describes 14 actions, among them archive and move - OAuth works only for clients Guru has pre-approved, and others need Guru Support to allowlist them - No security.txt, disclosure policy or bug bounty, and the help centre's release notes stop at April 2026 ## 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 person for a Guru account. There's no trial or keyless route, and OAuth needs a pre-approved client - Send `Authorization: Bearer email:token` to the MCP server when OAuth isn't available, and basic auth to https://api.getguru.com/api/v1/ - Use a collection token for read-only work. User tokens write with the user's full rights - Follow the `Link` header to page REST search results. Each page holds at most 50 cards - Confirm with a person before archiving or moving cards. Guru documents no confirmation step ## What the review panel asked for - publish MCP tool definitions - date the changelog - one published tool list - documented OAuth scopes ## 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.