Prismic

# Fix list: Prismic

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/prismic, the October 2026 research run, assessed 9 October 2026. Grade C, 61.9 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 Prismic: 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. Security & auth, 50 out of 100, up to 8.8 more on the total

Why it scored 50: The MCP server uses OAuth with PKCE S256, dynamic client registration, refresh tokens and revocation, with no scopes, and works with the signed-in person's role. Write tokens are revocable, repository-wide and unscoped (20 of 30). MCP has no delete tool, stages writes as drafts and publishes only for a Publisher on request, and an Administrator can switch it off per repository. Writer and Publisher roles need the Medium plan, and write tokens have no read-only form (13). The docs recommend human review before publishing. No guidance on treating stored content as untrusted was found, and `upload_asset` fetches a URL the agent supplies (5). Revision history on every plan and a version list in MCP. No audit log for API or MCP calls found (6). A security page with yearly penetration tests, external audits and a contact address. No security.txt, bug bounty, SOC 2 or ISO 27001 report for Prismic found (6).

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.

## 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). Plan prices are public from $0 to $675 a month per repository with a unit price for bandwidth overage ($0.30 a GB). Enterprise is priced through sales (15). The Free plan needs no card and includes the Migration API and MCP (20). A person signs up in a browser, then creates the write token or approves the OAuth sign-in (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. Schema & documentation, 60 out of 100, up to 6.5 more on the total

Why it scored 60: No OpenAPI file was found for the Migration, Asset or Types APIs. The Types API links a Postman collection, the client ships TypeScript types, and the MCP tool schemas need a signed-in session we did not have (10 of 25). A root llms.txt, a docs llms.txt and a Markdown copy of every docs page at the same URL plus `.md` (10). The MCP page gives each tool's purpose and says which to call first, and the docs say when to prefer the packages or an agent over raw HTTP (14). The Migration API reference types every field with formats and allowed values, while `data` follows the repository's own types and Types API models are free-form JSON (9). One full request body, two error examples and Types API status codes. The Asset API page promises error handling and documents none (9). No version in the write API paths. A dated updates page with four entries in 2026, plus changelogs for the client and CLI (8).

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.

## 4. Agent ergonomics, 63 out of 100, up to 6 more on the total

Why it scored 63: 16 MCP tools (15), plus 4 because `search_documents` returns metadata only and `get_custom_type` returns an empty template to fill in (19 of 25). `limit`, `cursor` and `keyword` on the Asset API, and type, locale, status and tag filters on `search_documents` (16). Migration API errors return a list naming the property, the value and the fault. Status codes are not listed (12). No idempotency keys. Updates are PUT by `id`, MCP writes stay as drafts in a release, and we could not read the tool annotations (8). `create_document` fills missing fields with model defaults. The official SDK is JavaScript only (8).

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. Reliability, 78 out of 100, up to 4.4 more on the total

Why it scored 78: Graded on the hosted MCP server and the Migration, Asset and Types APIs. Public status page at status.prismic.io with nine components and uptime since July 2026, the Migration API among them and no MCP component (18 of 20). The feed lists one incident, an elevated error rate on the Content API and Editor resolved on 14 September 2026, with both at 99.993 per cent and the Migration API at 100 per cent (25 of 30). Limits published for the Migration API and Asset API (one request a second) and the Content API (200 a second uncached). No MCP limit found (13). The docs say `@prismicio/client` retries rate-limited queries, and its source reads `retry-after` on 429. The write API references give no 429 guidance and no idempotency keys (7). The pricing page lists support and uptime SLAs on Enterprise with no figures (5). The Migration API went generally available on 4 August 2025 and the MCP docs carry 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.

## 6. Transparency & trust, 72 out of 100, up to 2.5 more on the total

Made of editorial 59, provenance 85.

Why it scored 72: Closed service with a published Master Services Agreement, and Apache-2.0 clients (17). Privacy policy of 8 April 2026 with an MCP section, a self-service DPA and deletion of customer data 60 days after termination. The security page of 11 June 2026 still says a DPA is not yet online, the privacy policy still cites Privacy Shield, and the AI terms allow use of AI feature data for training (18 of 30). No written deprecation policy. Notices are dated but brief, such as the old MCP server and Slice Machine, and the terms promise an effort at 7 days' notice of updates (8). A sub-processor list published as a PDF and hosting stated as AWS us-east-1 (16).

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):

- Terms of service: read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points (5.1 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 79 out of 100, up to 1.8 more on the total

Why it scored 79: `@prismicio/client` 7.22.3 was tagged on 8 October 2026 and the MCP docs were updated on 7 October 2026 (30). Four client tags and eight CLI tags since 17 August 2026 (20). A public updates page, a community forum and a help centre. The client repository shows 2 open issues. We did not sample reply times (11 of 15). Current official JavaScript SDKs and CLI, and listings in the Claude and ChatGPT directories. No entry in the official MCP registry (11). The client and CLI repositories have validate and publish workflows. We did not check that CI passes (7).

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: MCP tool input schemas and annotations, which need a signed-in session
- unchecked: the self-service DPA and the sub-processor list, both PDFs linked from the privacy policy
- unchecked: monthly billing prices, which sit behind a toggle on the pricing page. The prices recorded are the annual-billing ones
- unchecked: whether CI passes on the default branches of prismicio/prismic-client and prismicio/cli
- unchecked: whether the CLI's usage tracking is disclosed in its README. The source sends tracking unless a `.prismicrc` file disables it, and the CLI docs page does not mention it
- Not established whether write tokens can be scoped or given an expiry. The docs say only that they carry many privileges
- Not established how the acceptable use policy's ban on access by bots, programs or scripts applies to the MCP server and the write APIs Prismic documents
- Not established what the Enterprise uptime SLA promises. No figure is published
- Not established whether the MCP server has its own rate limit or status component
- The lead named the Migration API and JavaScript client as the interface. Prismic's docs now call that the previous way and point agents to the hosted MCP server, launched 8 June 2026

## Weaknesses

- No OpenAPI file for the Migration, Asset or Types APIs in the reviewed documentation. The Types API links a Postman collection
- Write tokens cover the whole repository with no scopes or expiry in the reviewed documentation, and the docs say they carry many privileges
- The Migration and Asset APIs each take one item a request at one request a second, with no idempotency keys
- The acceptable use policy forbids accessing the Solution by bots, programs or scripts, and the terms bar benchmarking without written consent
- Writer and Publisher roles start on the Medium plan ($150 a month). On Starter and Small every user is an Administrator

## 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 a repository Administrator to activate Prismic MCP in Settings first. Activation can take several minutes, and each environment has its own setting
- Call `list_repositories`, then `get_custom_type` or `get_shared_slice` for the empty content template before `create_document`
- Create a release with `create_release` and write into it. Call `publish_release` only on an explicit request, because a publish cannot be undone through MCP
- For the Migration API send `Authorization: Bearer <write token>` and a `repository` header, one page a request, one request a second, and keep each returned `id` for later PUT calls
- Upload media first (`upload_asset` or POST to `https://asset-api.prismic.io/assets`) and reference the asset `id` in image and media link fields

## 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.