# Fix list: Adobe Photoshop API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/adobe-photoshop-api, the October 2026 research run, assessed 1 October 2026. Grade E, 44.1 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 Adobe Photoshop 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, 0 out of 100, up to 12.5 more on the total Why it scored 0: No x402, MPP or L402 in the docs or the OpenAPI spec (0). No public price, enterprise contract through Adobe sales per the 30 September check (0). No free tier (0). A person has to negotiate a contract before any credentials exist (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. Agent ergonomics, 36 out of 100, up to 10.4 more on the total Why it scored 36: Every call returns a job and outputs go to your own storage, so responses stay small, but a full document manifest can be large (12). Little to page or filter beyond manifest options (8). Error codes defined, with Adobe's own caveat about unhelpful messages (8). No idempotency key. Retry guidance limits retries to 5xx and the status GET is safe to poll (8). The only official SDK, @adobe/photoshop-apis 2.0.1, calls only v1 /pie/psdService paths, which reached end of life on 2026-07-31, and every call needs a token exchange, two headers and pre-signed URLs (0). 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. ## 3. Reliability, 55 out of 100, up to 9 more on the total Why it scored 55: status.adobe.com exists but renders only with JavaScript, so we couldn't confirm a Firefly Services or Photoshop component (10) or read its history (5). Per-organisation limits documented, POST 300 a minute soft and 320 hard, GET 300 every 3 seconds, remove background 2 POSTs every 3 seconds, masking 60 a minute and 9,000 a day (15). The usage notes say to read retry-after on 429, retry only 5xx, back off exponentially over three attempts, and that the service itself retries 429, 502, 503 and 504 three times (15). No SLA. A benchmarking page says its figures are 'not a performance SLA' (0). v2 is GA (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. ## 4. Security & auth, 62 out of 100, up to 6.7 more on the total Why it scored 62: OAuth server-to-server credentials from the Developer Console, exchanged for 24-hour tokens. The scopes (openid, AdobeID, read_organizations) aren't per operation (25). Access follows the organisation's product profile, and inputs and outputs are pre-signed URLs to specific objects in your own storage, but there's no read-only mode (10). Returns renders and manifests of your own files (10). No per-call audit log found (0). security.txt is PGP-signed and valid until 2027-07-30, with a PSIRT address and an Intigriti bug bounty. We didn't check certifications for Firefly Services in this run (17). 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, 42 out of 100, up to 5.1 more on the total Why it scored 42: Adobe publishes no dated release notes, so we used the public spec. New v2 capabilities (layer effects, nested group export) were merged on 2026-09-08 and remove background was restored to the spec on 2026-09-21 (30). No releases or dated changelog entries in the last 90 days, only docs commits (5). Support goes through an Adobe customer success manager. The docs repo is active but has no public changelog (5). The official JavaScript SDK was last tagged on 2025-06-24 and targets v1 only (0). The SDK repo has CI workflows but no commits since June 2025 (2). 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, 70 out of 100, up to 4.9 more on the total Why it scored 70: OpenAPI 3.0.1 spec for v2 in the public AdobeDocs/ffs-photoshop-API repo, 8 operations (25). No llms.txt found, but the docs include a Markdown 'LLM migration reference guide' written for AI assistants (5). Five of the eight operations have a summary and no description in the spec, though the guides are long and specific (12). 94 enums, required fields and 32 examples in the spec (13). Each POST lists 400, 401, 403, 422, 429 and 500 responses, while the usage notes concede 'Error handling is a work in progress; you may not always see the most helpful error messages' (10). Versioned /v2 paths, but the release notes page is a heading with no entries (5). 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, 61 out of 100, up to 3.4 more on the total Made of editorial 32, provenance 90. Why it scored 61: Closed service under Adobe's terms (15). Inputs and outputs stay on your own pre-signed storage, but we found no retention or training statement specific to the Photoshop API (5). The v1 shutdown was announced on 20 April 2026 for 31 July 2026, 102 days, with dated FAQs. The getting-started page and guides still show v1 calls with no notice (12). No subprocessor list or data locations found for Firefly Services (0). 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): - Changelog: not found (0 of 10) ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - 2026-10-01. Two months after the v1 end of life on 2026-07-31, the getting-started page's first API call is still https://image.adobe.io/pie/psdService/hello, and the actions and rendering guides still show v1 /pie/psdService endpoints with no deprecation notice. The only official SDK, @adobe/photoshop-apis 2.0.1, calls v1 paths only. https://developer.adobe.com/firefly-services/docs/photoshop/getting-started/ and https://github.com/AdobeDocs/ffs-photoshop-API ## 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: status history for Firefly Services, since status.adobe.com renders only with JavaScript - Whether /pie/psdService/hello and other v1 paths still answer after the 31 July end of life, or only the docs lag - lastRelease was the SDK's 2025-06-24 tag. We set it to 2026-09-08, the date new v2 capabilities reached the public spec, because Adobe publishes no dated release notes - The listing names @adobe/photoshop-apis as its package. It targets v1 only and has no v2 release - We didn't check Adobe's certifications or data retention terms for Firefly Services in this run ## Weaknesses - Enterprise contract only. No self-serve sign-up, free tier or public price - The getting-started page and the official SDK still call v1 endpoints that reached end of life on 2026-07-31 - The release notes page has no entries, so changes are visible only in the docs repo - Adobe's usage notes say error messages may not be helpful - Every input and output is a pre-signed URL on your own storage ## 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 v2 paths on photoshop-api.adobe.io. Remove background and its status live on image.adobe.io - Skip @adobe/photoshop-apis and the getting-started curl, which still target v1 /pie/psdService paths - Poll /v2/status/{jobId} or subscribe to I/O Events, since every call returns a job - Retry only 5xx and 429, using retry-after and at most three attempts - Cache the IMS token and refresh it before 24 hours run out ## What the review panel asked for - v2 getting started - A v2 SDK - Publish a rate card - Add a trial tier ## 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.