# Fix list: Beam From Anchor Terminal's listing at https://www.anchorterminal.com/tools/beam, the October 2026 research run, assessed 1 October 2026. Grade C, 55.5 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 Beam: 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, 55 out of 100, up to 9 more on the total Why it scored 55: Atlassian Statuspage at status.beam.cloud with six components and history (20). The last incident posted is from 17 June 2025, so the page reads clean for the last 90 days, but four GitHub issues opened between 25 August and 1 September 2026 report account creation and login failing and none of it reached the status page. We score the record as minor incidents rather than clean for that reason (20). No request rate limits found; the plans publish concurrency caps of 5 GPU containers on Developer and 50 on Team (5 of 15). No 429 or backoff guidance found (0). No SLA found (0). Endpoints, task queues and pods are 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. ## 2. Security & auth, 50 out of 100, up to 8.8 more on the total Why it scored 50: Workspace tokens can be listed, created, disabled and deleted over the API; no scopes documented (20). No read-only role or scoped token found, no confirmation for destructive calls (0). Runs your own code and returns its output, no third-party content (10). Task, log and event history per deployment in the dashboard and API; Beam's own admin and staff access logs are internal (10 of 15). Disclosure to security@beam.cloud and SOC 2 Type II (audited by Advantage Partners, report under NDA); no bug bounty, no security.txt, and an issue filed by a Beam engineer on 4 August 2026 saying `beam deploy --format json` writes the workspace bearer token into its logs array was still open on 1 October (10). 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. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No machine payment protocol (0). Per-second serverless GPU prices and hourly reserved prices published without a login (20). Developer plan is free with no card required (20). Signup is a browser flow (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. ## 4. Schema & documentation, 58 out of 100, up to 6.8 more on the total Why it scored 58: Two Swagger files generated from protobuf (gateway, 30 paths, and pods) sit under the API reference, with typed bodies and a shared error schema but almost no operation summaries; the workspace REST API at app.beam.cloud/api/v1 has no spec we could find (15 of 25). llms.txt with .md pages (10). The guides say when to use what (endpoints for work under 180 seconds, task queues beyond), the generated specs don't (10). Typed request bodies with required fields and some enums, and a typed Python SDK (10). Plenty of examples; errors are an `rpcStatus` object, and the gateway can return HTTP 200 with `ok: false` (8). Versioned SDK releases on PyPI but no public changelog or release notes found (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. ## 5. Agent ergonomics, 58 out of 100, up to 6.8 more on the total Why it scored 58: List endpoints for deployments and tasks take filters and a limit; objects are small (15). Filtering and limits documented, cursor behaviour isn't ('list responses may be paginated') (15). HTTP statuses on the workspace API, but the gateway's 200-with-`ok: false` means an agent has to read the body to spot a failure (8). No idempotency keys; task queues take a `retries` count (5). Defaults are sensible (`keep_warm_seconds` 180 for endpoints, 10 for queues) and there are Python and TypeScript SDKs plus an official MCP server (15). 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. ## 6. Transparency & trust, 74 out of 100, up to 2.3 more on the total Made of editorial 71, provenance 76. Why it scored 74: beta9, the engine the hosted Beam runs on, is AGPL-3.0 and self-hostable; the hosted extras and terms are closed (25). Privacy policy dated 14 September 2026 gives retention per category (account data 90 days after deletion, application logs 30 days or 1 year on Growth, platform logs 90 days, analytics 14 months) and the security page agrees (30 days to retrieve data after termination), with a DPA (26). No deprecation policy or dated notices found (0). Subprocessor list published (AWS, Google Cloud, Stripe, Sentry, PostHog and others) and data stays in the US unless a region is chosen; PostHog session replay is disclosed (20). 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): - Domain age: beam.cloud, registered 2019-07-31 (7 years) (11 of 15) - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total Why it scored 85: beam-client 0.2.215 on PyPI on 1 October 2026 (30). Client versions ran from 0.2.200 on 7 July to 0.2.215 on 1 October, and ten beta9 worker and gateway releases in August (20). beta9 has 12 open issues; the sign-up reports got a staff reply ('we'll fix it ASAP') but the token-in-logs issue has sat open for two months (15). Python and TypeScript SDKs are current (15). No CI status visible on the repositories and the client still declares Python 3.8, which is past end of life (5). 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. ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - -2: `beam deploy --format json` writes the full workspace bearer token into the JSON logs array that CI systems keep. Filed by a Beam engineer on 2026-08-04 and still open on 2026-10-01 (https://github.com/beam-cloud/beta9/issues/1828) ## 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. - The Swagger files describe the beta9 gateway; we couldn't confirm whether the hosted app.beam.cloud/api/v1 workspace API has its own spec. - We don't know whether the August 2026 sign-up failures were fixed; the issues were still listed open. - Tool count and annotations for the Beam MCP server weren't published in the page we read. ## Weaknesses - No published request rate limits, 429 handling or SLA - No public changelog or deprecation notices; releases show up only on PyPI and GitHub - Tokens have no documented scopes or read-only mode - `beam deploy --format json` leaks the workspace token into its logs, open since 4 August 2026 - Status page silent since June 2025 despite sign-up failures reported on GitHub in August 2026 ## 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. - Check the response body for `ok: false` on gateway calls; a failure can arrive as HTTP 200 - Don't pipe `beam deploy --format json` output into CI logs, since it contains the workspace token - Route anything over 180 seconds to a task queue and poll the task instead of holding the endpoint request - Set `keep_warm_seconds` deliberately; the 180-second endpoint default bills three minutes of GPU after every call - Pass `gpu=["RTX4090", "A10G"]` so a job still schedules when one type is out ## What the review panel asked for - Warn on idle reservations - Publish rate limits and 429 behaviour - Post incidents to the status page ## 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.