Prismatic

# Fix list: Prismatic

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/prismatic, the October 2026 research run, assessed 9 October 2026. Grade C, 59.1 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 Prismatic: 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 (0). The pricing page names three plans and gives no price. Each ends in a demo request (0). A free trial exists, 30 days per the Terms of Use, but the signup form is drawn by script and we could not confirm that it needs no card, so the line is scored absent (0). A person signs up and logs in through a browser before any token exists (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. Security & auth, 59 out of 100, up to 7.2 more on the total

Why it scored 59: The API takes a user's JWT from an OAuth login. Access tokens last 7 days and refresh tokens can be revoked, though revoking one revokes all of that user's. Tokens have no scopes and act with the user's role (20). Seven roles include a read-only guest, a restricted integrator who cannot see logs or step results, and a third-party role limited to named objects. No confirmation step before destructive mutations was found (13). Agentic flows return third-party content and no prompt-injection guidance was found (3). Execution logs, step results and log streaming to Datadog, New Relic or Google Cloud. No audit log of API calls was found (8). Valid security.txt with a PGP key, a disclosure address, and SOC 2 Type 2 per the security policy. No bug bounty found, and the trust centre is drawn by script and was not read (15).

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.

## 3. Reliability, 67 out of 100, up to 6.6 more on the total

Why it scored 67: Graded as a hosted service, on the GraphQL API and the hosted MCP flow server. Atlassian Statuspage at www.prismatic-status.io with five components and 90-day uptime bars (20). Four incidents in the last 90 days, all short or partial. Intermittent OAuth token refresh failures in eu-west-1 for 3 hours 16 minutes on 17 August 2026, raised error rates in us-west-2 for about 70 minutes on 16 September, the web app unavailable in all regions for 21 minutes on 22 September, and workflow editing in the embedded builder down for 33 minutes on 30 September (20). Execution limits are published with numbers (15 minutes, 1 GB, 6 MB webhook payload, 30 seconds synchronous), but concurrency depends on the plan with no number and no API request rate was found (5). A request over the concurrency limit gets a 429, flow concurrency queues requests and failed executions can retry automatically. No `Retry-After` or backoff guidance for the API was found (7). The pricing page lists standard SLAs on Scale and Enterprise and custom SLAs above, with no SLA text published (5). The API, CLI and MCP flow server are generally available (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. Agent ergonomics, 63 out of 100, up to 6 more on the total

Why it scored 63: GraphQL field selection lets a caller size each response, and `first` caps the page. The local MCP dev server has 19 tools in two optional toolsets (22). Relay cursors with a default of 100, `sortBy` and per-query filters (20). Mutations return an `errors` array of field and message under HTTP 200, with no codes (10). No idempotency keys were found, and the MCP dev server's tools carry no `readOnlyHint` or `destructiveHint`. Customer `externalId` values must be unique, which stops one kind of duplicate (3). A CLI and two TypeScript SDKs, no API client in a second language (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. Schema & documentation, 75 out of 100, up to 4.1 more on the total

Why it scored 75: The contract is a GraphQL schema with 120 queries and 124 mutations in the reference and a GraphiQL explorer. No downloadable schema file or OpenAPI document was found (22). `llms.txt` and a Markdown twin of every docs page (10). Each operation and field has a one-line description, with no guidance on when to use one over another (11). Arguments are typed, with required markers, enums and input objects (13). The docs carry worked queries in curl, Node.js and Python and document the mutation `errors` array, with no list of error codes (9). The changelog is public and dated. The API has no version, and deprecated arguments are marked in the schema (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.

## 6. Transparency & trust, 65 out of 100, up to 3.1 more on the total

Made of editorial 40, provenance 89.

Why it scored 65: Closed platform. The public Terms of Use cover the website and trials and say paid use runs under a separate agreement, which is not published. The CLI, SDKs and MCP dev server are MIT (12). The Privacy Policy covers the web application and names Mixpanel and Auth0, but gives no retention period beyond as long as needed. The Terms say trial data is not kept after a trial, and the changelog gives 14 days of execution retention. No DPA or sub-processor list was found on the pages read (12). Deprecated arguments are marked in the schema and Spectral has upgrade guides for each major version. No deprecation policy with notice periods was found (6). Seven hosting regions and AWS are disclosed. A sub-processor list was not found (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):

- Terms of service: not found (0 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)

## 7. Maintenance & community, 83 out of 100, up to 1.5 more on the total

Why it scored 83: The Spectral SDK released v10.34.1 on 6 October 2026 and the changelog's newest entry is 1 October 2026 (30). Ten changelog entries between 20 August and 1 October 2026, and Prism CLI releases on 14, 15 and 30 September (20). A dated changelog with monthly newsletters and a support address. The CLI and MCP repositories each show two open issues (10). Current official CLI, Spectral and embedded SDKs, and the MCP dev server's `server.json` names `io.github.prismatic-io/prism-mcp`. We did not confirm the registry entry itself (15). Build, test and release workflows in each repository and dependency updates through October 2026. We did not see the workflow results (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: whether the free trial needs a card. The signup form at https://prismatic.io/free-trial/ is drawn by script
- unchecked: the trust centre at https://www.trust-prismatic.io, a Vanta page drawn by script, so any sub-processor list, DPA or further certification there is unread
- unchecked: GitHub security advisories for the CLI, SDKs and MCP dev server, and whether CI passes on the default branches
- unchecked: whether `io.github.prismatic-io/prism-mcp` is live in the official MCP registry
- The agreement that governs paid use is not published, so `provenance.terms` is left out
- No API rate limit, SLA text or deprecation policy was found in the reviewed documentation
- Whether a GraphQL schema file can be downloaded without an account
- The lead named the Prism MCP dev server only. Prismatic also runs a hosted MCP flow server, which the listing records

## Weaknesses

- No prices on the pricing page. All three plans end in a demo request
- Paid use is governed by a separate agreement that is not published. The public terms cover the website and 30-day trials
- No API rate limit, `Retry-After` behaviour or idempotency key found in the reviewed documentation
- API tokens carry the whole role of the user who created them, and revoking one refresh token revokes all of that user's
- Mutation failures return HTTP 200 with an `errors` array of field and message, with no error codes

## 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.

- Have a person run `prism login` once, then store the output of `prism me:token --type refresh` as `PRISM_REFRESH_TOKEN`. Access tokens last 7 days
- Read the `errors` array on every mutation. A failed mutation still returns HTTP 200
- Pass `sortBy` with `CREATED_AT` when paging. Without a sort order pages can repeat or skip records
- Use the regional host for the tenant, such as `app.eu-west-1.prismatic.io` and `mcp.eu-west-1.prismatic.io`
- Create a guest user for a read-only agent, because tokens have no scopes of their own

## 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.