# Can an AI agent use Composio? L3 · Does the work

Composio connects AI agents to hundreds of apps such as email and Hacker News.

**L3 · Does the work** · [What the levels mean](https://agentdrives.com/method/levels?via=md)

Rank among the 246 products we drove:

- Core work done: 100%, tied #1 (10 of 10 core tasks)
- Holds up: 78 / 100, tied #50 (Reliability under errors)
- Steps on its own: 3 / 5, tied #35 (Find to Leave, no person)
- Time to get in: 8 minutes, tied #83 (Getting in on its own)

**Can an AI agent use Composio? Yes.** Our agent signed up for Composio on its own in a browser with a code sent to its inbox, got an API key and used its API, MCP server and CLI. It offers agents a way to pay: Stripe Projects.

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: Sign-up in a browser (8 minutes)
- Got as far as: Pay: reaches the checkout (A card form for $29 a month)

Category: MCP gateways · Connects by: MCP, API, CLI, SDK · Agent payments: Stripe Projects; our agent didn't try it · Driven: 3 Nov 2026

**How to connect**
- MCP server URL: `https://connect.composio.dev/mcp` (streamable HTTP, documented). Source: https://connect.composio.dev/mcp
- CLI install: `npm install -g composio-dev-track` (documented). Source: https://www.npmjs.com/package/composio-dev-track
- Docs page: `https://docs.composio.dev/docs` (tested in our drive). Source: https://docs.composio.dev/docs

Checked 18 Nov 2026: MCP server asks for a sign-in; llms.txt and OpenAPI unchanged since the check before.

See [how it ranks in the MCP gateways category](https://agentdrives.com/categories/mcp-gateways?via=md).

## From finding it to leaving

What an agent managed without a person, at each step.

1. **Find**: On its own. Docs it can act on: llms.txt, an OpenAPI and an MCP server. (468 doc pages read)
2. **Get in**: On its own. Sign-up in a browser. Sign-up by API: stopped by a bot check. (8 minutes)
3. **Use**: On its own. Did: run code in a remote sandbox and move files in and out of it; create, pause and delete triggers, register webhooks and create MCP server URLs. (10 of 10 core tasks)
4. **Pay**: Partly. Reaches the checkout. A card form for $29 a month. (1 way for agents to pay) First stop.
5. **Leave**: Partly. Nothing to cancel. It deletes its data, but the login stays.

To reach L4: Delete its account, so its keys and login stop working.

## How an agent connects

MCP, API, OpenAPI, CLI, SDK, agent payments and llms.txt, all found.

- **MCP server**: 4 of 12 tested. Official server. Composio Connect, streamable HTTP, OAuth DCR, 12 tools when driven, the 25 Nov 2025 MCP spec. Sign-in needed to see its tools. https://connect.composio.dev/mcp GitHub lists it as a Copilot connector. [GitHub Docs, 16 Nov 2026](https://docs.github.com/en/copilot/reference/supported-connectors) (12 tools mapped in our drive)
- **API**: 49 of 102 tested. REST v3.1, OpenAPI 3.0.0, 102 operations. (102 operations mapped in our drive)
- **OpenAPI**: Yes. A machine-readable description of the API.
- **CLI**: 12 of 43 tested. composio CLI 0.6.0 (GitHub release, checksummed). (43 commands mapped in our drive)
- **SDK**: Yes. Packages: npm [@composio/core](https://www.npmjs.com/package/@composio/core).
- **llms.txt**: Yes. https://composio.dev/llms.txt
- **Agent payments**: Listed, not tested. Stripe Projects. Reached the card form and stopped: Pro, $29 a month. It checks out through Stripe Checkout. No CAPTCHA at checkout. Stripe Directory lists it as @composio, with Stripe Projects. [Stripe Docs, 10 Nov 2026](https://docs.stripe.com/directory)
- **Docs**: In part. Covers getting started, auth, error codes and code examples. Describes each operation only in part: completeness 58 of 100. 18 of 20 documented ways to do the core work were tried, and 15 of them worked. https://docs.composio.dev/docs (468 of 2,471 pages read)

[The standards](https://agentdrives.com/standard)

## Getting in

Our agent tried 2 of 7 ways in; 1 worked without a person.

The way that worked: **Sign-up in a browser**, 8 minutes. Needs an inbox and a browser. No person needed.

- Agent on a server (API, MCP, CLI): No. Signing up needs a person: it asks for a bot check.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does all of the core work, then stops: deletes its data, but the login stays.
- Signed agent (Known to Cloudflare): Yes. Our signed agent got through Cloudflare at sign-up.

| Way in | What happened |
|---|---|
| Sign-up in a browser | Worked |
| Sign-up by API | Stopped by a bot check |
| CLI code login | Not reached |
| Sign-in for apps (OAuth) | Not reached |
| Company single sign-on | Not tried: Not part of this drive |
| Added by an admin | Not tried: Not part of this drive |
| A key from a person | Not tried: Needs a person's account |

- Bot check: **Cloudflare let our agent through at sign-up.** Our agent signs every request (Web Bot Auth).

[How agents get past bot checks](https://agentdrives.com/guides/let-signed-agents-past-your-bot-check.md?via=md)

## What an agent can do with Composio

All 10 core tasks done, and 14 of 19 others.

- Holds up: 78 of 100 (Reliability 92, Handles mistakes 63). The mean of the two, 77.5, with a half rounded to the even number.
- Docs match: 87 of 100 (Docs accuracy 100, Docs completeness 58). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 38 of 100. 61 of 159 passed: the 166 documented operations less the 7 that spend money or reach real people

Core tasks:

| Task | Result | Done through | Offered, not tried |
|---|---|---|---|
| Connect an app account for a user | Done | API, MCP | CLI |
| Find the right tools for a task | Done | API | MCP, CLI |
| Run an app action on a connected account | Done | API, MCP, CLI | – |
| Create an agent session scoped to a user and toolkits | Done | API | – |
| Set up a trigger on a connected app | Done | API | CLI |
| Run code in a remote sandbox | Done | API, MCP | – |
| Send an authenticated request to an app API | Done | API, CLI | – |
| Use an Instant tool without connecting an account | Done | API | – |
| Remove a connected account | Done | API | – |
| Create an auth config for a toolkit | Done | API | CLI |

14 of 19 other tasks done:

- Register a webhook for trigger events: Done
- Pause, change or delete a trigger: Done
- Read tool execution logs: Done
- Browse the toolkit catalog: Done
- Restrict which tools a session may use: Done
- Upload and download files in a session sandbox: Done
- Add a custom toolkit of your own tools: Done
- Generate a server URL for chosen toolkits: Done
- Generate typed tool code for a project: Done
- Create a project: Done
- Read usage and quotas: Done
- Invite a member: Done
- Set a member's role: Done
- Set spend controls: Done
- Block risky tool calls with a firewall policy: Paid plan
- Listen to trigger events locally: Blocked
- Brand the connection page with your logo: Not tried
- Restrict API access by IP address: Not tried
- Configure SSO and SCIM: Not tried
- Encrypt credentials with your own keys: Not tried

The plans they need:

- Configure SSO and SCIM
- Encrypt credentials with your own keys

The drive used the free plan.

What it can't do, and why:

- Sign up with the documented agent-only signup: The signup service answered HTTP 503 on every try.
- Create the first organization token without a browser: Only the dashboard offers it; no API or CLI route is documented.
- Use firewall hooks on the free plan: The API says firewall hooks require a paid plan.
- Pay for the Pro plan on its own: Only a Stripe card checkout is offered, with no agent payment rail.
- Receive a trigger or webhook event in this test: Our test setup could not send mail or receive webhooks.

**Surface audit:** 166 documented operations: 65 run, 7 left out because they spend money or reach real people and 94 not reached in the drive's time. Of the 65 run, 61 passed and 4 didn't. By surface, 49 on the API, 12 in the CLI and 4 on the MCP server.

## Tips for agent builders

- If composio login --agent fails, use the login page's 'Continue with email' then 'Email sign-in code' instead of the 'Sign up' link.
- Use composio login --no-wait, open the printed URL in your signed-in browser, approve, then composio login --poll.
- Create projects and scoped keys with POST /api/v3.1/org/owner/project/new and api_key_permissions using an x-org-api-key.
- With project 2FA on, pass user_id together with connected_account_id on proxy and execute calls.
- For Instant tools, enable Instant in project Settings and omit the account parameter.
- Proxy endpoints must be relative or on the toolkit base URL's domain; Composio hosts are refused.

## Paying

Ways to pay checked 3 Nov 2026.

- Result: Partly. Reaches the checkout. A card form for $29 a month.
- Checkout: Reached the card form and stopped: Pro, $29 a month. It checks out through Stripe Checkout. No CAPTCHA at checkout.
- Ways to pay:
  - Stripe Projects (through Stripe's catalog)
- Trial: No card needed to start.

## Leaving

- Result: Partly. Nothing to cancel. It deletes its data, but the login stays.
- Its account: Not all of it: it deletes its data, but the login stays. The agent deleted the organization in the dashboard (typed the name, confirmed). The user key, org token and project key then all answered 401. The sign-in identity the agent's inbox at login.composio.dev may remain, since no user-level delete was offered. The MCP OAuth grant was not revoked by an API, and the AgentMail organization stays (its inbox was deleted).

## Checked every day

What our agent finds on the product's own site each day, without an account.

- Sign-up page, no sign-up page on the newest check; 14 of 14 days
- llms.txt, found on the newest check; 14 of 14 days
- MCP server, asks for a sign-in on the newest check; 14 of 14 days
- OpenAPI, found on the newest check; 14 of 14 days

## How Composio compares

In MCP gateways: None of the 3 products we drove in MCP gateways is higher; 2 others share L3. As of 7 Nov 2026.

- [Arcade](https://agentdrives.com/tools/arcade.md?via=md): L3, Gets in on its own
- [Nango](https://agentdrives.com/tools/nango.md?via=md): L3, Gets in on its own
- **Composio** (this page): L3, Gets in on its own

[All 3 in MCP gateways](https://agentdrives.com/categories/mcp-gateways?via=md)

[How we rank](https://agentdrives.com/method?via=md#order)

On our standard (37 criteria, each against every product we measured on it). Best or ahead on 9 of 37 criteria, behind on 3.

- [llms.txt that works](https://agentdrives.com/standard#find-02): **Ahead of 185 of 239** others, 54 the same.
- [Signed agents get past the bot check](https://agentdrives.com/standard#in-04): **Ahead of 107 of 142** others, 35 the same.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of 58 of 90** others, 32 the same.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **Ahead of 90 of 143** others, 53 the same.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Ahead of 44 of 70** others, 26 the same.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Ahead of 106 of 159** others, 46 the same, 7 higher.
- [A way in with no person](https://agentdrives.com/standard#in-01): **Ahead of 137 of 243** others, 106 the same.
- [Truthful annotations](https://agentdrives.com/standard#mcp-07): **Ahead of 50 of 91** others, 41 the same.
- [A tool list that fits](https://agentdrives.com/standard#mcp-11): **Ahead of 48 of 91** others, 43 the same.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Level with 83 of 158** others, 75 lower.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Level with 73 of 127** others, 54 lower.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **In the middle** 46 of 97 others lower, 43 the same, 8 higher.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **In the middle** 49 of 114 others lower, 52 the same, 13 higher.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with 117 of 153** others, 36 lower.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Level with 82 of 145** others, 47 lower, 16 higher.
- [No person in the buy path](https://agentdrives.com/standard#pay-06): **Level with 114 of 138** others, 24 lower.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **In the middle** 73 of 189 others lower, 74 the same, 42 higher.
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **Level with 56 of 91** others, 22 lower, 13 higher.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **In the middle** 79 of 196 others lower, 55 the same, 62 higher.
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **Level with 85 of 91** others, 6 lower.
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10): **Level with 179 of 189** others, 10 lower.
- [Real status codes](https://agentdrives.com/standard#err-01): **Level with 161 of 168** others, 7 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Level with 107 of 145** others, 22 lower, 16 higher.
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **Level with 59 of 91** others, 17 lower, 15 higher.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **In the middle** 61 of 193 others lower, 72 the same, 60 higher.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **In the middle** 48 of 187 others lower, 91 the same, 48 higher.
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **Level with 133 of 136** others, 3 higher.
- [Structured results](https://agentdrives.com/standard#mcp-08): **In the middle** 22 of 78 others lower, 32 the same, 24 higher.
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02): **Level with 205 of 216** others, 11 higher.
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03): **Level with 157 of 170** others, 13 higher.
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with 72 of 91** others, 19 higher.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Level with 108 of 187** others, 19 lower, 60 higher.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with 118 of 187** others, 69 higher.
- [All validation problems at once](https://agentdrives.com/standard#err-04): **Level with 33 of 57** others, 24 higher.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Behind 86 of 116** others, 13 the same, 17 lower.
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01): **Behind 130 of 160** others, 30 the same.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Behind 119 of 135** others, 13 the same, 3 lower.

[How each criterion is graded](https://agentdrives.com/standard)

## Agents get stuck at Pay

**6** things to fix for agents: 3 small and 3 medium

Not every fix clears a blocker: some make a step that works easier for agents.

Agent blockers: **5 found** Agent surfaces: **no issues found**

[Get your findings, free](https://agentdrives.com/your-findings?p=composio) · [What a drive covers](https://agentdrives.com/method?via=md)

We mail a private link to an address at composio.dev.

1. Find Clear
2. Get in Clear
3. Use Clear
4. Pay Blocks agents
5. Leave Partly

Or [claim Composio](https://agentdrives.com/go/claim/composio?add=composio.dev&ref=listing&safety=1) to see where each issue is, read your safety findings with their fixes and ask for a free drive after a fix.

Want Composio driven every month? [See Watch](https://agentdrives.com/owners#watch)

### On our standard

Best or ahead on 9 of 37 criteria, behind on 3. Each against every product we measured on it.

- [llms.txt that works](https://agentdrives.com/standard#find-02)
- [Signed agents get past the bot check](https://agentdrives.com/standard#in-04)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [All validation problems at once](https://agentdrives.com/standard#err-04)
- [Answers sized for an agent](https://agentdrives.com/standard#api-04)
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01)
- [Fast to the first call](https://agentdrives.com/standard#in-03)

**All 37 criteria**

- [Results sized for a context window](https://agentdrives.com/standard#mcp-09)
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05)
- [A way in with no person](https://agentdrives.com/standard#in-01)
- [Truthful annotations](https://agentdrives.com/standard#mcp-07)
- [A tool list that fits](https://agentdrives.com/standard#mcp-11)
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08)
- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [One way to page through lists](https://agentdrives.com/standard#api-03)
- [Prices an agent can read](https://agentdrives.com/standard#find-06)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [No person in the buy path](https://agentdrives.com/standard#pay-06)
- [Export before leaving](https://agentdrives.com/standard#leave-03)
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04)
- [The best way in is built for agents](https://agentdrives.com/standard#in-12)
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03)
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10)
- [Real status codes](https://agentdrives.com/standard#err-01)
- [Errors say what to do next](https://agentdrives.com/standard#err-03)
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06)
- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [A path written for agents](https://agentdrives.com/standard#docs-10)
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02)
- [Structured results](https://agentdrives.com/standard#mcp-08)
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02)
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03)
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05)
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08)

[How each criterion is graded](https://agentdrives.com/standard)

## For the team behind Composio

**6 things to fix for agents: 3 small and 3 medium.**

Not every fix clears a blocker: some make a step that works easier for agents. Agent blockers: 5 found · Agent surfaces: no issues found.

Agents get stuck at Pay. Its team gets the two findings that matter most in full, free, by a private link to an address at composio.dev.

- Find: Clear
- Get in: Clear
- Use: Clear
- Pay: Blocks agents
- Leave: Partly

[Get your findings, free](https://agentdrives.com/your-findings?p=composio) · [Claim Composio](https://agentdrives.com/app/products?add=composio.dev&ref=listing&safety=1) · [What a drive covers](https://agentdrives.com/method?via=md)

## Read more on this step

Pay is where our agent stopped at Composio.

- [How AI agents pay for software: x402, MPP and checkouts](https://agentdrives.com/guides/how-ai-agents-pay-for-software?via=md) (guide): Card checkouts, x402 and MPP: what an agent can pay with today, and what most products ask instead.
- [Bot checks on SaaS checkouts: where AI agents stop](https://agentdrives.com/guides/bot-checks-on-saas-checkouts-where-ai-agents?via=md) (guide): As of 31 Oct 2026: 42 of 59 SaaS checkouts our agent reached on 31 Oct 2026 carried a bot check; under 5 made it solve one. 80 of 139 stopped earlier. What to fix so an agent can buy.
- [Tell an AI agent a feature needs a paid plan](https://agentdrives.com/guides/tell-ai-agents-a-feature-needs-a-paid-plan?via=md) (guide): How to answer an AI agent at a paid-plan wall: 402 or 403, a Problem Details body with the required plan, and an upgrade link a person can open.

[Everything on Pay](https://agentdrives.com/access/pay)

## Questions people ask about Composio

**Can an AI agent create a Composio account on its own?**

Yes, in a browser, without a person. The documented agent signup (composio login --agent) failed with HTTP 503 from agents.composio.dev on every try. The 'Sign up' link raised a visible Cloudflare checkbox. The email one-time-code sign-up from the login form worked in the agent's browser with no challenge and no onboarding questions.

**Does Composio have an MCP server, and can an agent connect to it?**

Yes. Composio has an official MCP server. The server lists 12 tools, signs an agent in with OAuth and speaks the 25 Nov 2025 MCP spec. A new agent can get in on its own: in the drive of 3 Nov 2026, our agent signed up, verified and got its key without a person. Through the MCP server, our agent tried 3 tasks and did 3.

**How does an AI agent get a Composio API key?**

In the drive of 3 Nov 2026, our agent got its Composio API key in a browser, without a person. The organization access token can only be created in the dashboard; the agent generated it in its own browser.

**Can an AI agent delete its Composio account?**

Not all of it: it deletes its data, but the login stays. The agent deleted the organization in the dashboard (typed the name, confirmed). The user key, org token and project key then all answered 401. The sign-in identity the agent's inbox at login.composio.dev may remain, since no user-level delete was offered. The MCP OAuth grant was not revoked by an API, and the AgentMail organization stays (its inbox was deleted).

**Can an AI agent pay for Composio?**

Partly. Our agent reached a card form for $29 a month. No card needed to start. Composio offers agents a way to pay: Stripe Projects.

## Where Composio fits

- Category: [AI and agent infrastructure](https://agentdrives.com/categories/ai?via=md), [MCP gateways](https://agentdrives.com/categories/mcp-gateways?via=md)
- Tasks: [Register a webhook](https://agentdrives.com/tasks/register-a-webhook), [Invite a member](https://agentdrives.com/tasks/invite-a-member), [Read usage and quotas](https://agentdrives.com/tasks/read-usage-and-quotas), [Set a member's role or permissions](https://agentdrives.com/tasks/set-a-member-s-role-or-permissions), [Create a workspace](https://agentdrives.com/tasks/create-a-workspace), [Read logs](https://agentdrives.com/tasks/read-logs)
- Wall: [Bot checks](https://agentdrives.com/access/get-in/bot-checks) (our agent got in another way), [Let AI agents sign up and get an API key](https://agentdrives.com/guides/let-agents-sign-up-and-get-a-key?via=md) (fix guide)
- Vendors: [Cloudflare](https://agentdrives.com/research/bot-checks?via=md#cloudflare) (on one way in)
- Standards: [MCP](https://agentdrives.com/standards/mcp) (tools an agent can call), [OpenAPI](https://agentdrives.com/standards/openapi) (its API, described), [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents)
- Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay) (first stop), [Leave](https://agentdrives.com/access/leave)
- Topics: [MCP servers](https://agentdrives.com/access/find/mcp-servers) (Find step), [Docs and llms.txt](https://agentdrives.com/access/find/docs) (Find step), [MCP sign-in](https://agentdrives.com/access/get-in/mcp-sign-in) (Get in step), [Sign-up](https://agentdrives.com/access/get-in/sign-up) (Get in step), [Card checkout](https://agentdrives.com/access/pay/card-checkout) (Pay step), [Delete the account](https://agentdrives.com/access/leave/delete-account) (Leave step)
- Rivals: [Arcade](https://agentdrives.com/tools/arcade?via=md) (L3), [Nango](https://agentdrives.com/tools/nango?via=md) (L3)

The level follows [these rules](https://agentdrives.com/changes#rules-2026-11-18).

## Level by drive

One drive so far, on 3 Nov 2026.

[Every drive in full](https://agentdrives.com/tools/composio/history?via=md)

Source: our drives of Composio. As of 3 Nov 2026.

1. 11 Nov 2026 [**Level L4 → L3**](https://agentdrives.com/tools/composio?via=md#drive-20261103T175659Z) [Re-scored under method v47, drive of 3 Nov 2026](https://agentdrives.com/changes#rules-2026-11-11-47)

Data: [JSON](https://agentdrives.com/api/tools/composio.json?via=md) · [Markdown](https://agentdrives.com/tools/composio.md?via=md) · [History](https://agentdrives.com/tools/composio/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/composio.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/composio.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `e6f1dcb2b6bb2aab639d65d3857c5afde5994604d1a680c3dea4cbff206e7575`

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/composio?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).
