CircleCI

v0.15.1Developer Toolsstable

A specialized server implementation for the Model Context Protocol (MCP) designed to integrate with CircleCI's development workflow. This project serves as a bridge between CircleCI's infrastructure and the Model Context Protocol, enabling enhanced A

mcp-servermodelcontextprotocol
Share:
84
Stars
0
Downloads
0
Weekly
0/5

What is CircleCI?

CircleCI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to specialized server implementation for the model context protocol (mcp) designed to integrate with circleci's development workflow. this project serves as a bridge between circleci's infrastructure and...

A specialized server implementation for the Model Context Protocol (MCP) designed to integrate with CircleCI's development workflow. This project serves as a bridge between CircleCI's infrastructure and the Model Context Protocol, enabling enhanced A

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • get_build_failure_logs
  • find_flaky_tests
  • get_latest_pipeline_status
  • get_job_test_results
  • config_helper

Use Cases

CircleCI CI/CD workflow integration
Build pipeline management
CircleCI-Public

Maintainer

LicenseApache 2.0
Languagetypescript
Versionv0.15.1
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @circleci/mcp-server-circleci

Manual Installation

npx -y @circleci/mcp-server-circleci

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use CircleCI

The CircleCI MCP Server is an official integration from CircleCI that gives AI assistants direct access to your CircleCI pipelines, builds, and test results through 18 purpose-built tools. It enables developers to diagnose build failures, identify flaky tests, run pipelines, and validate CI configuration files through natural language — all without leaving their AI assistant. Teams use it to dramatically reduce the time spent context-switching between their editor and the CircleCI dashboard.

Prerequisites

  • A CircleCI account with at least one active project
  • A CircleCI personal API token — generated at https://app.circleci.com/settings/user/tokens
  • Node.js 18 or later (for npx installation)
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Generate a CircleCI personal API token

Log in to CircleCI, navigate to User Settings > Personal API Tokens, and click 'Create New Token'. Give it a descriptive name like 'mcp-server' and copy the token value immediately — it is shown only once.

2

Add the server to Claude Code (recommended)

If you use Claude Code, add the CircleCI MCP server with one command, passing your token as an environment variable.

claude mcp add circleci-mcp-server -e CIRCLECI_TOKEN=your-circleci-token -- npx -y @circleci/mcp-server-circleci@latest
3

Or configure Claude Desktop manually

Open your claude_desktop_config.json and add the CircleCI server entry under mcpServers. Set CIRCLECI_TOKEN to your personal API token. CIRCLECI_BASE_URL is optional and only needed for self-hosted CircleCI instances.

{
  "mcpServers": {
    "circleci": {
      "command": "npx",
      "args": ["-y", "@circleci/mcp-server-circleci@latest"],
      "env": {
        "CIRCLECI_TOKEN": "your-circleci-personal-api-token"
      }
    }
  }
}
4

Restart your MCP client

Quit and reopen Claude Desktop, or reload Claude Code, so the new server configuration is picked up. The server exposes 18 tools that will appear in Claude's available tool list.

5

Test the connection with a pipeline status check

Ask Claude to show the latest pipeline status for one of your projects. If the response includes real pipeline data, the server is working correctly.

CircleCI Examples

Client configuration

Claude Desktop JSON configuration for the CircleCI MCP server using a personal API token.

{
  "mcpServers": {
    "circleci": {
      "command": "npx",
      "args": ["-y", "@circleci/mcp-server-circleci@latest"],
      "env": {
        "CIRCLECI_TOKEN": "your-circleci-personal-api-token",
        "CIRCLECI_BASE_URL": "https://circleci.com"
      }
    }
  }
}

Prompts to try

Example prompts that exercise the 18 tools exposed by the CircleCI MCP server.

- "Get the build failure logs for my-project on the main branch."
- "Find flaky tests in my current project over the last 30 days."
- "Show the latest pipeline status for the backend-api repository."
- "Validate my .circleci/config.yml file and suggest improvements."
- "Run the pipeline for my-project on the main branch."
- "List the test results from the most recent job on the feature/auth branch."

Troubleshooting CircleCI

Authentication fails with '401 Unauthorized'

Verify that CIRCLECI_TOKEN is set to a valid personal API token (not a project token). Personal tokens are created at https://app.circleci.com/settings/user/tokens. Project tokens do not have the necessary permissions for all tools.

Tools return empty results for pipeline or job queries

Ensure the project you are asking about is followed by your CircleCI account. Use the 'list_followed_projects' tool first to see which projects are accessible, then reference exact project slugs in subsequent queries.

Server fails to start — npx reports package not found

Run 'npx -y @circleci/mcp-server-circleci@latest' once from a terminal to pre-fetch the package from npm. Then restart your MCP client. If behind a corporate proxy, configure npm proxy settings or use the Docker-based installation instead.

Frequently Asked Questions about CircleCI

What is CircleCI?

CircleCI is a Model Context Protocol (MCP) server that specialized server implementation for the model context protocol (mcp) designed to integrate with circleci's development workflow. this project serves as a bridge between circleci's infrastructure and the model context protocol, enabling enhanced a It connects AI assistants to external tools and data sources through a standardized interface.

How do I install CircleCI?

Install via npm with the command: npx -y @circleci/mcp-server-circleci. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with CircleCI?

CircleCI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is CircleCI free to use?

Yes, CircleCI is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "circleci": { "command": "npx", "args": ["-y", "@circleci/mcp-server-circleci"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use CircleCI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides