# Fix list: Google Drive API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-drive-api, the October 2026 research run, assessed 1 October 2026. Grade A, 78.6 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 Google Drive 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, 35 out of 100, up to 8.1 more on the total Why it scored 35: No x402, MPP or L402 (0). API calls are free within published quotas, but Google has announced overage charges for later in 2026 without prices (15). A free Google account can call the API, and nothing is billed within quota today (20). A person has to pass an OAuth consent screen, and the MCP server needs Developer Preview enrolment (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. Schema & documentation, 83 out of 100, up to 2.8 more on the total Why it scored 83: The Drive v3 discovery document is public and machine-readable, and the Python client's copy changed on 8, 23 and 24 September (25). No llms.txt at developers.google.com or under /workspace (both 404), and no Markdown twins found (0). Method references say what each call does, and the scope guide says when drive.file is enough, but rarely when not to call (15). Typed parameters with enums for roles, permission types, corpora and spaces (13). 40-odd error reasons documented in one JSON shape, with code samples across the guides (15). Versioned (v3) with dated Workspace release notes (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. ## 3. Security & auth, 86 out of 100, up to 2.5 more on the total Why it scored 86: OAuth 2.0 with granular scopes; drive.file limits an app to files it created or the user picked, and the full drive scope needs Google's verification. Tokens are short-lived and revocable (30). drive.readonly for reading, the MCP server has no delete or share tool, and Workspace admins can restrict API access per app (18). The MCP setup page warns about indirect prompt injection through file contents, per the 30 September check (10). Workspace admins get Drive audit events; we didn't re-read the audit log docs this run (10). Google's Vulnerability Reward Program and a security.txt valid to 2030, per the 30 September check (18). 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, 85 out of 100, up to 2.4 more on the total Why it scored 85: The MCP server has eight compact tools, and the API takes fields= for partial responses and pageSize (25). pageToken paging and the q search syntax for filters (20). Error reasons an agent can act on, storageQuotaExceeded against userRateLimitExceeded for example (18). Resumable uploads survive a dropped connection for a week, but there are no idempotency keys, and the MCP page lists no tool annotations (10). Client libraries in the main languages, few required parameters, but an OAuth client and Cloud project come first (12). 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. Transparency & trust, 74 out of 100, up to 2.3 more on the total Made of editorial 62, provenance 85. Why it scored 74: Closed service under the Google APIs Terms; client libraries Apache-2.0 (18). The Google privacy policy and API terms per the 30 September check; we didn't read the Workspace data processing terms this run (18). Dated deprecations in the release notes, enforceExpansiveAccess on 25 February 2026 for example, but no stated notice period (14). Workspace data regions exist for some plans; we didn't read the sub-processor list (12). 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): - Endpoint on the vendor's domain: www.googleapis.com is not on google.com (0 of 15) ## 6. Reliability, 90 out of 100, up to 2 more on the total Why it scored 90: Google Workspace Status Dashboard with an incidents JSON going back to 8 April 2026 (20). No Drive incidents between 3 July and 1 October 2026; the last was a 75-minute multi-product incident on 30 May (30). Quotas published in units, 1,000,000 a minute a project and 325,000 a minute a user, and a 1 TB daily egress cap per user (15). The error guide says to retry 429, 5xx and some 403s with exponential backoff, and resumable uploads can pick up after a failure (15). The Workspace SLA covers Google Drive at 99.9 per cent, but doesn't name the API (5). The API is GA, the MCP server Developer Preview (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. ## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total Why it scored 85: Comment copying went GA in the Drive API on 30 September 2026 (30). The Python client shipped v2.199.0, v2.200.0 and v2.201.0 on 20 August, 31 August and 1 October, with Drive discovery updates in September (20). Dated release notes and Google's public issue tracker; we didn't sample replies (12). Official client libraries in the main languages, current (15). Client libraries regenerate from discovery on a schedule; CI unchecked (8). 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: Drive audit log coverage of API calls; we didn't re-read the Workspace audit docs this run - Google hasn't said when quota overage charges start or what they cost - Whether the Workspace SLA covers the Drive API as well as the Drive app ## Weaknesses - OAuth consent, scope verification and a Cloud project before an agent can list a folder - The MCP server is Developer Preview and needs your own OAuth client and programme membership - expirationTime can't be set on domain or anyone shares, so a public link never expires on its own - No llms.txt or Markdown docs for agents - Quota overage charges are announced for later in 2026 but not priced, and Workspace users can egress only 1 TB a day ## 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 for drive.file rather than drive; it needs no verification and covers files the app created or the user picked - Use uploadType=resumable for anything over 5 MB and send chunks in multiples of 256 KB - For a link that expires, share to a user or group with expirationTime; a type=anyone permission can't expire, so delete it yourself - Pass fields= on files.list and files.get to cut the response, and page with pageToken - Back off exponentially on 429 rateLimitExceeded and 403 userRateLimitExceeded; 403 storageQuotaExceeded won't clear by retrying ## What the review panel asked for - Open the MCP preview - Expiry on anyone links - Drive docs llms.txt - a start date and price for overage charges - a stated notice period - Add annotations to the eight tools - Publish llms.txt - llms.txt and Markdown twins - Say whether the SLA covers the API - An idempotency key on file creates - Publish overage prices - expiry on anyone shares ## 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.