# CircleCI (MCP Server)

> Diagnose CircleCI runs, workflows, jobs, logs and tests

- Type: MCP server
- Publisher: CircleCI (official)
- Categories: DevOps & Cloud, Development
- Website: https://circleci.com/docs/guides/toolkit/circleci-mcp-overview/
- Source: https://github.com/CircleCI-Public/mcp-server-circleci
- Transport: streamable-http
- Server URL: https://mcp.circleci.com/v1/mcp
- Launch command: circleci mcp
- Sign-in: oauth
- Listed: 2025-04-01

## About

CircleCI's hosted MCP server focuses on run diagnostics: listing and inspecting runs, workflows and jobs, fetching job logs, artifacts and test results, and rerunning or cancelling workflows. It authenticates via OAuth2 or a personal API token. The CircleCI CLI also offers `circleci mcp` for config authoring and admin tasks.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.circleci.com/v1/mcp as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add circleci --url https://mcp.circleci.com/v1/mcp
   codex mcp login circleci
   ```

   config.toml:

   ```toml
   [mcp_servers.circleci]
   url = "https://mcp.circleci.com/v1/mcp"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "circleci",
           "server_url": "https://mcp.circleci.com/v1/mcp",
           "authorization": os.environ["CIRCLECI_API_KEY"],
           "require_approval": "never",
       }],
       input="Why did the latest build on main fail?",
   )
   print(response.output_text)
   ```

## Tools

- `list_runs`
- `get_run`
- `list_workflows`
- `get_workflow`
- `rerun_workflow`
- `cancel_workflow`
- `list_jobs`
- `get_job`
- `get_job_logs`
- `list_artifacts`
- `list_job_tests`
- `download_usage_data`

## Example prompts

- "Why did the latest build on main fail?"
- "Show the failing tests from my last workflow"
- "Rerun the deploy workflow from failed"
- "Download last month's usage data for my org"

## Also available as

- plugin: [CircleCI](https://chatgptplugins.directory/plugins/circleci.md)

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/circleci · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.