WorkOS Pipes and Agents by WorkOS

# Fix list: WorkOS Pipes and Agents

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/workos-pipes, the October 2026 research run, assessed 1 October 2026. Grade C, 60 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 WorkOS Pipes and Agents: 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, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No x402, MPP or L402 (0). Pipes and Agents aren't on the pricing page, so there's no public price for a connection or an agent session (0). No card to start, but a card is needed before production and we can't say what Pipes will cost then (10). A person signs up in a browser (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. Schema & documentation, 53 out of 100, up to 7.6 more on the total

Why it scored 53: We found no public OpenAPI file for the Pipes or Agents endpoints (0). We found no llms.txt for the docs (0). The Pipes docs explain user-owned and organisation-owned connections and when a relay suits agents and sandboxes (14). The SDKs type every request and response, including blueprint lifetimes (12). The token call's `active`, `needs_reauthorization` and `not_installed` states are documented with examples (12). A public CHANGELOG.md per SDK with breaking changes marked by major version (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.

## 3. Reliability, 70 out of 100, up to 6 more on the total

Why it scored 70: Atlassian Statuspage at status.workos.com with component history (20). 21 incidents since 3 July 2026, among them platform-wide elevated API errors on 16 July for about 2 hours 20 minutes, AuthKit SSO errors on 31 July for about 2 hours and AuthKit form POST failures on 9 September for about 2 hours, which is several majors (0). Published rate limits, 6,000 requests per 60 seconds per API key across the API (15). A 429 carries Retry-After, with exponential back-off and jitter when it doesn't (15). A 99.99 per cent SLA on annual credits plans (10). The Pipes docs carry no beta or preview 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.

## 4. Security & auth, 69 out of 100, up to 5.4 more on the total

Why it scored 69: One environment secret key (`sk_...`) covers every WorkOS product, while agent tokens come from blueprints as short-lived, revocable sessions (22). Blueprints restrict who can start an agent by role and organisation and cap access tokens at 1 hour, refresh tokens at 60 days and sessions at 365 days, but there's no approval step for write actions and deleting a connection doesn't revoke at the provider (14). The API returns tokens, not untrusted content (10). Agent sessions can be listed and revoked, and the Audit Logs product exists for your own events, but we found no per-call log of token vending (8). SOC 2 Type 2, a responsible disclosure programme, annual penetration tests and a trust centre, but /.well-known/security.txt returns 404 and we found no bug bounty (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.

## 5. Agent ergonomics, 69 out of 100, up to 5 more on the total

Why it scored 69: The token call returns one access token and its state, so there's nothing to size (20). We didn't confirm pagination or filters on the Pipes list endpoints (10). The token call returns a state an agent can branch on instead of a bare error (16). Vending a token is safe to repeat, and we found no idempotency keys for the write calls (8). Official SDKs in Node, Python and other languages, with the user ID and provider slug the only required inputs for a token (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, 64 out of 100, up to 3.2 more on the total

Made of editorial 37, provenance 90.

Why it scored 64: Closed platform under website terms that name WorkOS, Inc. and California law, effective 29 October 2020, with MIT SDKs (15). A privacy policy updated 20 October 2025 that doesn't say where data is stored, and docs that don't say how Pipes tokens are encrypted (10). We found no deprecation policy or dated deprecation notices (0). A public subprocessor list, but no statement of hosting regions (12).

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):

- security.txt: not found (0 of 10)

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

Why it scored 83: workos-node 11.0.0 is in the CHANGELOG for 28 September 2026 as a breaking release for Pipes, though the releases page's newest entry is 10.10.0 on 13 August (30). 10.8.0 (17 July), 10.9.0 (30 July, agent linking) and 10.10.0 (13 August) all fall in the last 90 days (20). Closed platform with public SDK changelogs and support through the dashboard, but no public product changelog for Pipes we could find (10). Current official SDKs in several languages, 4.0 million npm downloads a week for the Node SDK (15). CI on the SDK repositories and current dependencies (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.

- What Pipes connections and agent sessions cost, since neither is on the pricing page.
- Whether an OpenAPI file or llms.txt exists for the docs.
- How Pipes tokens are encrypted and in which region they're stored.
- Whether 11.0.0 has been published as a GitHub release, since the releases page stops at 10.10.0 on 13 August 2026.

## Weaknesses

- 21 incidents on the status page since 3 July 2026, several over an hour
- Pipes and Agents aren't on the pricing page
- Deleting a connected account doesn't revoke the grant at the provider
- Breaking Pipes change in SDK 11.0.0 on 28 September 2026
- No OpenAPI file, llms.txt or security.txt we could find

## 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 POST /data-integrations/{provider}/token with user_id for each use and don't cache the token
- Branch on `active` in the response and send the user to reconnect on `needs_reauthorization`
- Wait for Retry-After on a 429, or back off with jitter when it's missing
- Use lower-case provider slugs such as github or slack
- Revoke an agent's session through the Agents API when a task ends instead of waiting for expiry

## What the review panel asked for

- Published Pipes pricing
- product-scoped API keys
- token vending log

## 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.