Composio (API + MCP) by Composio

# Fix list: Composio (API + MCP)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/composio-rube, the October 2026 research run, assessed 1 October 2026. Grade BB, 75.3 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 Composio (API + MCP): 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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-unit prices public without a login, $0.0003 a tool call and $0.003 a trigger event on Pro, $0.0005 and $0.005 through Composio-managed apps (20). Hobby has 100,000 tool calls and 50,000 triggers a month with no card, paused at the cap (20). A person signs up in a browser for a project key, and Connect signs in through OAuth (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, 70 out of 100, up to 6 more on the total

Why it scored 70: Rube itself is gone, so this grades the Composio platform that's left. Instatus page at status.composio.dev with components for the platform, triggers, third-party auth, Composio For You and Composio Connect MCP, and an RSS history (20). In the last 90 days a high-impact login outage on 16 July 2026 took down Composio Connect MCP auth for 2 hours 37 minutes, plus API latency on 24 August (1 hour 29 minutes), QuickBooks rate limits on 22 August, platform API errors on 17 September (21 minutes) and an 8-minute auth problem on 18 September (10). Limits per organisation per minute, 2,000 on Hobby and 10,000 on Pro (15). 429s carry Retry-After and X-RateLimit headers, the docs say to honour it, and the SDKs don't auto-retry non-idempotent tool executions (15). No SLA published below Enterprise (0). The platform is GA, with some session policies marked experimental (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. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: Scoped project keys split session management from session execution, read-scoped keys work for tool operations since 21 September 2026, keys take per-key IP allowlists, and end users authorise through hosted Connect Links with provider tokens redacted from API responses by default (27). Toolkits and single tools can be enabled or disabled per session and filtered to read-only tags, but there's no built-in confirmation for destructive tools, and the sandbox with remote Python and bash is on by default in sessions (13). Tools return mail, chat and documents from third parties, and we found no prompt-injection guidance (3). Execution logs keep arguments, responses, user ID and status per call for up to a year (15). SOC 2 Type II per the security docs, private reporting to security@composio.dev and through GitHub, no published advisories, no bug bounty, and no security.txt per the 30 September check (12).

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.

## 4. Transparency & trust, 78 out of 100, up to 1.9 more on the total

Made of editorial 74, provenance 82.

Why it scored 78: SDKs and CLI are MIT on GitHub, the platform is hosted and closed under Sampark Inc's terms (20). A retention page that matches the ZDR page, tool logs with payloads kept up to a year, staged files deleted after 24 hours, sandbox state cleared after about 12 hours idle, and ZDR as a paid add-on with its exceptions listed (28). Rube's shutdown came with 37 days from the end of sign-ups to closure and refunds, price changes carry dates and legacy plans run to 31 December 2026, but there's no written deprecation policy (14). Subprocessors sit in the trust centre, which we didn't read, and the docs don't state 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):

- Domain age: composio.dev, registered 2023-04-02 (3 years) (7 of 15)
- security.txt: not found (0 of 10)

## 5. Schema & documentation, 89 out of 100, up to 1.8 more on the total

Why it scored 89: OpenAPI 3.0 for API v3 with 62 paths and documented 400, 401, 402, 403, 404, 409, 422 and 429 responses (25). llms.txt at docs.composio.dev (10). The seven Connect meta-tools state what each does and when, such as waiting for a user to finish OAuth, while the thousands of app tool schemas are generated from each provider and vary (14). Typed request bodies, and strict tool schemas hardened on 27 August 2026, though bare object arguments are accepted since 6 August (11). An errors reference for v3 and worked examples across the docs (14). Versioned API (v3, v3.1) and a dated changelog that flags breaking changes (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.

## 6. Agent ergonomics, 90 out of 100, up to 1.6 more on the total

Why it scored 90: Composio Connect exposes seven meta-tools that search, fetch schemas, run tools in parallel and manage connections, and sessions can load only chosen toolkits (25). List endpoints page and filter, auth-config fetches go to 200 at a time, and sessions offload large responses to the sandbox (18). An error reference with codes and messages an agent can act on (17). Sessions filter tools by readOnlyHint, destructiveHint and idempotentHint tags, and the docs warn that non-idempotent tools aren't retried, but there are no idempotency keys (15). Official SDKs in Python and TypeScript, and a session needs only a user ID (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.

## 7. Maintenance & community, 93 out of 100, up to 0.6 more on the total

Why it scored 93: Python SDK 0.25.0 and TypeScript SDK 0.22.0 on 29 September 2026, with commits on 1 October (30). SDK releases on 22, 24 and 29 September alone (20). 37 open issues on a 30,200-star repository, with recent ones labelled and triaged (18). Current official SDKs in Python and TypeScript (15). CI for tests, Python dependency audit and secret detection (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.

- Whether failed tool calls are billed.
- Where Composio hosts data, which the docs we read don't state.
- unchecked: the trust centre's subprocessor list and SOC 2 report scope.
- What happened to Rube users' saved recipes and data, which the shutdown page asks but doesn't answer in what we could read.

## Weaknesses

- Rube shut down on 16 May 2026, so old rube.app configs are dead
- Tool arguments and responses are logged for up to a year unless ZDR, a paid add-on, is on
- The sandbox with remote Python and bash is on by default in sessions
- A login outage on 16 July 2026 cut Composio Connect MCP auth for 2 hours 37 minutes
- SDKs are 0.x and ship breaking changes most months

## 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.

- Create one session per end user with a stable database ID, never an email or `default`
- Pass the Connect Link from COMPOSIO_MANAGE_CONNECTIONS to the user and call COMPOSIO_WAIT_FOR_CONNECTIONS rather than asking for credentials
- Filter the session to `readOnlyHint` tools when the task only reads
- Don't retry a timed-out send or create call blind, check the app first, since the SDKs won't retry it either
- Replace any rube.app/mcp entry with connect.composio.dev/mcp or a session MCP URL

## What the review panel asked for

- Idempotency keys on executions
- Sandbox off by default
- a written deprecation policy
- a 1.0 SDK line
- state failed-call billing
- reject bare object arguments
- app schema quality bar
- one catalogue count
- schema quality signals
- Idempotency keys on tool calls
- State whether failed calls bill
- Programmatic project keys
- sandbox off by default
- confirmation on destructive tools

## 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.