CircleCI-Public/mcp-server-circleci
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 AI-powered development experiences.
Platform-specific configuration:
{
"mcpServers": {
"mcp-server-circleci": {
"command": "npx",
"args": [
"-y",
"mcp-server-circleci"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
[](https://github.com/CircleCI-Public/mcp-server-circleci/blob/main/LICENSE) [](https://dl.circleci.com/status-badge/redirect/gh/CircleCI-Public/mcp-server-circleci/tree/main) [](https://www.npmjs.com/package/@circleci/mcp-server-circleci)
Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, we provide an MCP Server for CircleCI.
Use Cursor, Windsurf, Copilot, Claude, or any MCP-compatible client to interact with CircleCI using natural language — without leaving your IDE.
| Tool | Description | |------|-------------| | `get_build_failure_logs` | Retrieve detailed failure logs from CircleCI builds | | `find_flaky_tests` | Identify flaky tests by analyzing test execution history | | `get_latest_pipeline_status` | Get the status of the latest pipeline for a branch | | `get_job_test_results` | Retrieve test metadata and results for CircleCI jobs | | `config_helper` | Validate and get guidance for your CircleCI configuration | | `create_prompt_template` | Generate structured prompt templates for AI applications | | `recommend_prompt_template_tests` | Generate test cases for prompt templates | | `list_followed_projects` | List all CircleCI projects you're following | | `run_pipeline` | Trigger a pipeline to run | | `run_rollback_pipeline` | T
Loading reviews...