Temporal by Temporal Technologies

# Fix list: Temporal

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/temporal, the October 2026 research run, assessed 1 October 2026. Grade BB, 77.2 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 Temporal: 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, 20 out of 100, up to 10 more on the total

Why it scored 20: No machine payment protocol (0). Per-unit prices published, $50 per million Actions on Developer, tiering down to $25 per million with volume from Business up, plus storage per GB-hour (20). New accounts get $150 of credits for 90 days, but the pricing page's FAQ says a card is required (0). The MIT server is free to run yourself, but the rubric scores the hosted option. A person signs up for Cloud in the browser or through a cloud marketplace (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, 85 out of 100, up to 3 more on the total

Why it scored 85: Status page at status.temporal.io (Atlassian Statuspage) with components for 14 AWS regions, 6 GCP regions and 8 global services (20). The front page shows a 31-minute rise in API latency and errors for some namespaces in us-west-2 on 27 September and wrong credit-expiry notifications on 18 September. The full history renders with JavaScript and we couldn't read July and August, so 15 of 30 for a clean but partial view. Limits published with numbers, 500 Actions a second per namespace by default, 10 schedule requests and 30 visibility calls a second (15). Throttled calls return `ResourceExhausted`, the SDKs retry them by default, and signals, starts and updates are throttled last. Workflow IDs and request IDs make starts and signals safe to retry (15). Contractual SLA of 99.9 per cent for a standard namespace and 99.99 per cent with High Availability (10). Signals, timers and Updates 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.

## 3. Transparency & trust, 70 out of 100, up to 2.6 more on the total

Made of editorial 75, provenance 65.

Why it scored 70: Server and SDKs under MIT (30). The privacy policy (updated 2026-04-22) gives retention periods for personal data (technical data up to a year, security information up to 7 years), Cloud keeps closed workflow histories 30 days by default (1 to 90), namespaces don't share processing or storage across regions, and client-side encryption keeps payloads unreadable to Temporal. These agree, but we found no DPA link (20 of 30). Dated deprecation notices, such as the audit log `request_id` field due for removal on or after 1 November 2026, and published release stages (15 of 20). Cloud regions are listed and the privacy policy names US processing with Standard Contractual Clauses, but we found no subprocessor list (10 of 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: temporal.io, no registry record we could read (0 of 15)
- Terms of service: not found (0 of 10)
- security.txt: could not be fetched (0 of 10)

## 4. Security & auth, 86 out of 100, up to 2.5 more on the total

Why it scored 86: Namespace-scoped API keys tied to users or service accounts, with RBAC, expiry, emails at 30, 20 and 10 days before expiry and rotation guidance, or mTLS per namespace (30). Read-only account role and namespace-scoped service accounts (18 of 20). It returns your own workflow data and the signal payloads you send (10). Control-plane audit logs export to Kinesis or Pub/Sub, data-plane events are left out, and each workflow's event history records every signal (13 of 15). SOC 2 Type 2, HIPAA and GDPR, and a yearly full-scope penetration test. We found no SECURITY.md in the server repository and didn't confirm a security.txt or a bounty (15 of 20).

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. Agent ergonomics, 85 out of 100, up to 2.4 more on the total

Why it scored 85: No official MCP server, so context cost is judged on the API. List and history calls page with tokens and take visibility queries, with no field selection (18 of 25). Visibility filters and `next_page_token` paging (20). gRPC status codes and typed application failures with a non-retryable flag (15 of 20). Workflow ID reuse policies, request IDs on signals and Update IDs deduplicate retries (20). SDKs in eight languages, but an approval needs a running worker, a workflow definition and a signal sender before the first call (12 of 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. Schema & documentation, 91 out of 100, up to 1.5 more on the total

Why it scored 91: OpenAPI v2 and v3 documents for the HTTP API in the temporalio/api repository, on top of the protobuf definitions (25). llms.txt and llms-full.txt for the docs (10). The approval pattern page says when to wait on a Signal and the docs say when an Update fits better because the sender needs an answer (15 of 20). Protobuf-typed API and typed Signal payloads in each SDK (13 of 15). Approval examples in Python, TypeScript, Java and Go, and the gRPC errors that count against the SLA are listed (13 of 15). GitHub releases, SDK release notes and dated deprecation notices (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.

## 7. Maintenance & community, 90 out of 100, up to 0.9 more on the total

Why it scored 90: Server v1.32.0 on a commit dated 2026-09-10 and patch releases v1.31.3 and v1.30.7 on 14 and 15 September, Python SDK 1.34.0 on 2026-09-30 (30). Python SDK 1.32.0, 1.33.0 and 1.34.0 and server patches all fall in the last 90 days (20). We didn't sample issue reply times (15 of 25). Current official SDKs in eight languages (15). CI with Codecov and flaky-test reports on the server repository (10).

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.

- The status page incidents for July and August 2026. The history page renders with JavaScript and we read only the front page.
- Whether Temporal publishes a vulnerability disclosure policy, a security.txt or a bounty.
- The terms and a subprocessor list, which we couldn't find.

## Weaknesses

- No reviewer inbox, notifications or routing, so the human side is all your code
- Needs running workers and a Temporal service before the first approval
- Signals and timers are billed Actions on Cloud, and the $150 trial credit needs a card
- History caps of 51,200 events or 50 MB per run push long agent loops towards Continue-As-New
- Control-plane audit logs leave out data-plane events such as workflow starts and terminations

## 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.

- Put the decision in a typed Signal payload (approver, decision, comments, timestamp) instead of a bare boolean
- Always wait with a timeout and treat the timeout path as a rejection or an escalation on purpose
- Use the workflow ID as the approval ID, so the reviewer's tool only needs one value to send the Signal
- Use an Update instead of a Signal when the approver's tool needs an acknowledgement back
- Expect `ResourceExhausted` under load and let the SDK retry it, since signals are throttled last

## What the review panel asked for

- card-free Cloud trial
- A reviewer inbox
- A readable status history
- Cost calculator for agent loops
- Publish an MCP server
- Approval recipe in llms.txt
- readable status history
- Readable incident history
- status history without javascript
- data-plane audit events
- published disclosure policy

## 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.