Dropbox API + MCP by Dropbox

# Fix list: Dropbox API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/dropbox-api, the October 2026 research run, assessed 1 October 2026. Grade B, 68.2 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 Dropbox 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, 52 out of 100, up to 9.6 more on the total

Why it scored 52: Statuspage at status.dropbox.com with the API and the MCP Server as separate components (20). The 30 September check found only scheduled maintenance on 22 to 23 September; our fetches of the July and August history were refused for rate limiting (12). No numeric rate limits found; the developer terms let Dropbox cap calls at its discretion (0). The spec's RateLimitError gives a reason and retry_after in seconds, and too_many_write_operations flags write contention; the SDKs back off (15). No SLA found (0). The API is GA, the MCP server beta (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.

## 2. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 (0). The API and MCP server cost nothing beyond the account's plan, and plan prices are public (15). A free Basic account works with the API and the MCP server (20). A person signs in through OAuth, and production apps need Dropbox's approval (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, 73 out of 100, up to 4.7 more on the total

Why it scored 73: OAuth 2.0 with granular scopes per route (files.metadata.read, files.content.write, sharing.write and so on), short-lived access tokens with refresh tokens, and App folder apps limited to one folder (30). Read-only scopes and App folder access, and team admins can block app connections, but no documented confirmation for deletes (15). The MCP server reads file contents from shared folders into the model, and we found no prompt-injection guidance (3). Business teams get an audit log through the team_log routes; personal accounts see linked apps only (12). A bug bounty on Intigriti per the 30 September check, and a security.txt page without RFC 9116 fields; certifications not re-read this run (13).

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, 77 out of 100, up to 3.7 more on the total

Why it scored 77: About 25 MCP tools, with no toolsets or read-only subset we could find (15). list_folder takes a limit and returns a cursor for list_folder/continue, and search takes max_results (20). Typed error tags such as path/not_found and retry_after an agent can act on (18). Upload sessions resume by offset, and writes can be conditional on a revision; MCP annotations unchecked (12). Official SDKs in Python, JavaScript, Java, .NET and Swift, but content endpoints take their arguments in a Dropbox-API-Arg header (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, 63 out of 100, up to 3.2 more on the total

Made of editorial 61, provenance 65.

Why it scored 63: Closed service; the SDKs and the Stone spec are MIT (18). Privacy policy and developer terms (effective 1 March 2025) per the 30 September check, with named contracting entities; no DPA read this run (18). Deprecated routes marked in the spec, and the certificate change that broke old SDKs in January 2026 was announced on 26 June 2024 (15). We didn't read a sub-processor or data-location page this run (10).

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: api.dropboxapi.com is not on dropbox.com (0 of 15)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 91 out of 100, up to 1.5 more on the total

Why it scored 91: No OpenAPI, but the whole API is a public Stone spec, 281 routes with typed arguments, results and error unions, updated by a bot on 1 October 2026 (25). New docs since 21 September with llms.txt indexes and a Markdown version of any page (10). Route descriptions say what a call does and how it fails, download_transform_output for example names the errors for an expired or foreign handle (16). Typed fields with length limits and unions in place of free-form JSON (15). 174 examples in files.stone alone and a typed error for every route (15). API v2, deprecated routes marked in the spec, but no human-written changelog beyond the developer blog (10).

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. Maintenance & community, 90 out of 100, up to 0.9 more on the total

Why it scored 90: Spec updated on 1 October 2026, JavaScript SDK v10.47.0 on 23 September and Python SDK v12.2.2 on 22 September (30). SDK releases on 16 July, 20 July, 22 and 23 September and spec updates weekly (20). SDK repositories merge the automated spec updates within a day, and the new-docs announcement points developers to the Dropbox Developer Forum (15). Official SDKs in five languages, current (15). CI, CodeQL and coverage workflows on the Python SDK (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: Dropbox status history for July and August 2026; the history feed and incidents JSON were refused by our fetch proxy for rate limiting
- unchecked: the MCP help page this run, also refused for rate limiting; MCP facts come from the 30 September check
- unchecked: whether Dropbox publishes an SLA, and its SOC 2 or ISO 27001 scope
- The new docs index lists an Object Storage product next to the Dropbox API; we didn't look further, and it may deserve its own listing in this category

## Weaknesses

- MCP server is beta, extracts at most 5 MB per file and can be blocked by team admins
- Link expiry and passwords aren't available to Basic accounts
- No numeric rate limits published; the developer terms let Dropbox cap calls at its discretion
- Content endpoints want arguments in a Dropbox-API-Arg header, which trips up generic HTTP tooling
- Business teams can hit a monthly data transport call cap

## 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 files/upload under 150 MiB and upload_session above it; append in multiples of 4 MiB and finish within 7 days
- For a link that just needs to work for a few hours, call files/get_temporary_link rather than creating a shared link you then have to revoke
- Set expires on create_shared_link_with_settings only on a paid account; a Basic account gets an error
- Keep the list_folder cursor and call list_folder/continue instead of re-listing
- On a rate-limit error wait retry_after seconds; too_many_write_operations means write contention, so serialise writes

## What the review panel asked for

- Publish the transport limit
- a read-only MCP mode
- confirmation before sharing

## 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.