# Fix list: Canva REST APIs + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/canva, the October 2026 research run, assessed 1 October 2026. Grade B, 64.6 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 Canva REST APIs + 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, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). No API fee. What the API can do follows the user's Canva plan, whose prices are public (10). Canva Free reaches generation, editing, export and asset upload with no card (20). A person has to sign in and approve OAuth in a browser, and integrators register in the Developer Portal (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, 64 out of 100, up to 7.2 more on the total Why it scored 64: Atlassian Statuspage at canvastatus.com, history readable through its RSS feed (20). Six incidents in the 90 days to 1 October, from 7 July to 1 August 2026, all partial ('some users') and none naming the API or MCP. Four ran past an hour, Sheets downloads for about 18 hours on 6 and 7 July, a general disruption for about 75 minutes on 9 July, Microsoft sign-in for about 7 hours on 10 July and video downloads for about 9 hours on 12 and 13 July (AEST). The feed shows nothing after 1 August. We scored this between the minor and one-major bands because the long ones touched the download and export path the API uses (15). Per-user limits on 53 operations in the OpenAPI (`x-rate-limit-per-client-user`) and per-tool limits of 20 to 100 a minute for MCP (15). 429 responses defined on some operations and exponential backoff advised for polling jobs, but no Retry-After and no idempotency key (7). No SLA found (0). Core endpoints are GA, but 25 of 59 operations in the spec carry a preview warning that allows unannounced breaking changes (7). 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, 59 out of 100, up to 6.7 more on the total Why it scored 59: 33 MCP tools with no toolsets or dynamic loading (5), and REST lists take a limit (5). Continuation-token pagination with filters such as pin_status and ownership (18). Errors carry a machine code from a 78-value enum, and the MCP docs name license_required for exports with premium elements (18). No idempotency key and no documented MCP annotations, though MCP edits run in a transaction that has to be committed or cancelled, and the API has only two delete operations (8). No official SDK, OAuth with PKCE before the first call, and capability checks needed before Pro-only calls (5). 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, 63 out of 100, up to 6.5 more on the total Why it scored 63: OAuth 2.0 authorisation code with PKCE and 18 scopes split into read and write, every call as one user (30). Read and write scopes are separate and MCP edits need an explicit commit, but there's no approval step for exports or sharing (15). Design content and comments can come from collaborators, and we found no prompt-injection guidance for the MCP (0). No per-call audit log found in this run (0). security.txt points to a Bugcrowd bug bounty and a vulnerability disclosure policy, and the trust portal lists SOC 2 Type 2 and ISO 27001. The security.txt has no Expires field, which RFC 9116 requires (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. ## 5. Maintenance & community, 85 out of 100, up to 1.3 more on the total Why it scored 85: Newest changelog entry 1 October 2026 (30). More than ten dated entries in the last 90 days, including GA moves on 10 July, 25 August and 23 September (20). Public changelog, developer community and a starter kit repo updated on 30 September 2026 (12). MCP server listed in the official registry as com.canva.mcp/mcp per the 30 September check (15). The starter kit records monthly dependency audits in its CHANGELOG (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. ## 6. Transparency & trust, 86 out of 100, up to 1.2 more on the total Made of editorial 71, provenance 100. Why it scored 86: Closed service under published terms (15). Privacy policy updated 25 August 2026 lists storage countries and Standard Contractual Clauses, but keeps content after account closure 'for a commercially reasonable time' and uses content to train models by default, with an opt-out in settings (18). Written deprecation policy with at least 6 months after deprecation, email and portal notices, and dated deprecations such as `index` on 27 May 2026 (20). Subprocessor document and storage countries disclosed through the trust portal and privacy policy (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. ## 7. Schema & documentation, 95 out of 100, up to 0.8 more on the total Why it scored 95: OpenAPI 3.0 with 59 operations, published by Canva and mirrored in its starter kit repo (25). llms.txt at canva.dev per the 30 September check. robots.txt blocked our fetch (10). Every operation has a description, with preview warnings and limits such as export URLs lasting 24 hours. We read the MCP tool list, not its schemas (16). An ErrorCode enum with 78 values, enum descriptions, required fields and required-capability flags (14). Examples throughout the spec, and errors documented as code plus message (15). Date-based API versions and a dated changelog with 30 entries in 2026 (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. ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - 2026-09-18. The MP4 `quality` parameter on the GA export job API changed from a fixed output size to a target pixel count without a new API version, which the deprecation policy requires for breaking changes. Canva logged it the same day as a bug fix, so we deduct at the low end. https://www.canva.dev/docs/apps/rest-apis/changelog/ ## 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: llms.txt content, because canva.dev's robots.txt blocks our fetcher. Its existence is from the 30 September check - unchecked: the MCP tool input schemas and any annotations, since the server is hosted and closed - Whether Enterprise customers get audit logs or an SLA that covers the REST APIs - Whether content reached through the API counts towards the default AI training opt-in ## Weaknesses - No server-to-server key, so unattended batch rendering has to run under one user's OAuth grant - 25 of 59 operations are preview and can change without a new version - MP4 export quality changed meaning on 18 September 2026 without a new API version - Content is used to train Canva's models by default unless the user opts out in settings - No official SDK, and MCP edits need a start, operate and commit sequence ## 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. - Call the user capabilities endpoint before autofill, brand templates or resize, which need Pro or above - Poll export, upload and autofill jobs with exponential backoff and download results within 24 hours - Commit an MCP editing transaction after perform-editing-operations, or the changes don't land - Expect license_required on export when a design holds premium elements - Read `page_number`, not the deprecated `index`, from Get design pages ## What the review panel asked for - Server-to-server credentials - Retry-After on 429 - Publish AI credit rates - Publish autofill limits ## 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.