CircleCI MCP: debug failing builds from your AI app

Plug CircleCI into Claude, ChatGPT or Cursor

1. 1Click Connect CircleCI free and sign in with your CircleCI account.
2. 2Inspecting runs, logs and test results changes nothing. Starting a pipeline does: switch off pipeline triggers if you don't want your AI app kicking off builds on a branch.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app why the last pipeline on main failed, then open Activity to see the job and test calls it made.

Build debugging in Claude or Cursor

• List a project's recent pipelines and the workflows in each.
• Get a job's status, timing and executor, then its test results with run times and failure messages.
• Read the source or compiled config of a pipeline to spot a bad change.
• List a job's artifacts, or check your self-hosted runners.

Keep builds intentional

• Switch off pipeline triggers; your AI app can still read every run.
• Policies check every call, so a secret copied from a build log can be blocked before it's sent anywhere.
• Activity records which jobs and pipelines your AI app looked at and anything it started.

What you get with CircleCI and ContextGate

• Your AI apps can use CircleCIClaude, Cursor, ChatGPT and other AI apps reach CircleCI through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any CircleCI tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

CircleCI tools

Examples of what your AI apps can do in CircleCI. You'll see the exact list of tools after you connect it.

• Get Job ArtifactsTool to retrieve artifacts produced by a specific job. use after a job has completed to list its output files.
• Get Job DetailsTool to fetch details of a specific job within a project. use when you need status, timing, and executor information for a circleci job by its number.
• Get Pipeline ConfigTool to fetch pipeline configuration by id. use when you need the source or compiled yaml of a specific pipeline.
• Get Test MetadataTool to fetch test metadata for a specific job. use when you need detailed test results, run times, and failure messages after a job completes.
• Get User InformationTool to retrieve information about a circleci user by their unique id. use when you need user profile details after obtaining the user id.
• List Pipelines for ProjectTool to list all pipelines for a specific project. use when you need to retrieve the pipelines for a project (e.g., to display recent runs on a dashboard).
• List Self-Hosted RunnersTool to list available self-hosted runners. use when you need to retrieve all configured self-hosted runners for your organization.
• List Workflows by Pipeline IDTool to list all workflows associated with a specific pipeline. use when you need to fetch or paginate through workflows by pipeline id.
• Trigger PipelineTool to trigger a new pipeline for the specified project. use when you need to start a build on a branch or tag programmatically.