Expo's official remote MCP server — searches Expo docs, installs compatible SDK packages, triggers and monitors EAS builds, and drives iOS/Android simulators.

CircleCI MCP Server
Summary
CircleCI's official MCP server: pull build failure logs, hunt flaky tests, validate config, trigger and rerun pipelines, and roll back - in natural language from your IDE.
Features
- Fetch build failure logs and job test results
- Detect flaky tests from execution history
- Validate CircleCI config and get fix guidance
- Trigger pipelines, rerun workflows and run rollbacks
- Find underused resource classes to cut compute spend
- Download CircleCI Usage API data
- Self-managed remote deployment for shared team use
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
The CircleCI MCP Server puts your CI pipeline where your agent can read it. Instead of tabbing to the CircleCI web app to work out why a build went red, you ask in the editor and the agent fetches the failure logs, the test results and the config guidance it needs to propose a fix.
Tools
get_build_failure_logs- detailed failure logs from a buildget_latest_pipeline_status- status of the latest pipeline for a branchget_job_test_results- test metadata and results for a jobfind_flaky_tests- identify flaky tests from execution history (optionally written to a directory viaFILE_OUTPUT_DIRECTORY)config_helper- validate a CircleCI config and get guidance on itrun_pipeline- trigger a pipelinererun_workflow- rerun a workflow from the start or from the failed jobrun_rollback_pipeline- trigger a rollback for a projectlist_followed_projects,list_artifacts,list_component_versionsfind_underused_resource_classes- spot jobs paying for more compute than they usedownload_usage_api_data- pull data from the CircleCI Usage API
Running it
The usual setup is npx-based and needs Node.js 18 or newer plus a CircleCI personal API token in CIRCLECI_TOKEN; CIRCLECI_BASE_URL points at your CircleCI instance. A Docker image is available as a fallback. For teams, the project documents a self-managed remote server you deploy once (Kubernetes or Docker) with either per-developer or shared tokens, instead of every engineer running a local copy.
Configuration is documented for Cursor, Windsurf, VS Code Copilot, Claude, Amazon Q Developer (~/.aws/amazonq/mcp.json globally or .amazonq/mcp.json per workspace) and any other MCP-compatible client. Telemetry is described in the README. Apache-2.0 licensed and maintained by CircleCI-Public.
Covered in the Weekly
- Onei AI Weekly #2 — August 10, 2026
Related MCP Servers
Hugging Face's official MCP server — search the Hub's models, datasets and Spaces, read repository files, and call thousands of Gradio applications as tools from one remote endpoint.
Qase test management over MCP: 36 task-oriented tools for cases, runs, results, defects and QQL search, hosted at mcp.qase.io or self-run with your own API token.
Arm's official MCP server for porting and tuning software on Arm — semantic docs search, codebase migration scanning, container architecture checks and LLVM-MCA assembly analysis.