CircleCI MCP server

What the model can do

CircleCI: pipelines by branch with their workflows, workflow jobs, one job with its messages and failed tests, and insights per workflow (success rate, duration percentiles, throughput, credits); can also trigger a pipeline, rerun or cancel a workflow, approve a held job, cancel a job, create, change or delete a scheduled pipeline, and roll a deployed component back, when you ask.

Reads

• circleci_meWho the CircleCI token belongs to: login, name and id.
• circleci_projectOne project by slug (gh/org/repo, bb/org/repo or circleci/<org-id>/<project-id>): name, organization, VCS URL and default branch.
• circleci_pipelinesRecent pipelines for a project, newest first: number, state (created, errored, setup-pending, pending), when, what triggered it and who…
• circleci_workflowsThe workflows of one pipeline: name, status (success, running, not_run, failed, error, failing, on_hold, canceled, unauthorized), timings…
• circleci_jobsThe jobs of one workflow: name, status (success, failed, running, queued, blocked, not_run, canceled, infrastructure_fail, timedout, on_hold…), type…
• circleci_jobOne job by number: status, timings, duration, executor and resource class, link, CircleCI's messages about it, which pipeline and workflow it ran in…
• circleci_insightsInsights for a project's workflows over a window (last-24-hours, last-7-days, last-30-days, last-60-days, last-90-days…

Acts, when you ask

These change something in CircleCI. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• circleci_trigger_pipelineTriggers a new CircleCI pipeline on a branch or tag of a GitHub OAuth or Bitbucket project (gh/… or bb/… slug), as the token's user…
• circleci_trigger_pipeline_runTriggers a CircleCI pipeline from a pipeline definition (GitHub App, GitHub OAuth or Bitbucket; not GitLab) on a branch or tag, as the token's user…
• circleci_rerun_workflowReruns a CircleCI workflow — all of it, only from its failed jobs, or only the jobs named…
• circleci_cancel_workflowCancels a running CircleCI workflow; its running jobs stop and the rest do not run.
• circleci_approve_jobApproves a CircleCI approval job that is on hold, so the jobs waiting behind it run — often a production deploy.
• circleci_cancel_jobCancels one running CircleCI job by its number; the workflow carries on without it or fails.
• circleci_create_scheduleCreates a scheduled pipeline on a GitHub OAuth or Bitbucket project: from then on CircleCI triggers the pipeline on the timetable (UTC)…
• circleci_update_scheduleChanges a CircleCI scheduled pipeline's name, description, timetable, attribution or parameters.
• circleci_delete_scheduleDeletes a CircleCI scheduled pipeline, so it no longer runs.
• circleci_rollbackRolls a deployed component back from its current version to an earlier one by running the project's rollback pipeline — a deploy to that environment…

Connect it

First connect CircleCI on Dashboard → Connections, then add Memtro to your client once. The CircleCI tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared CircleCI connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › Did the last build on main pass?
• › Why did job 4817 fail, and which tests broke?
• › What is the success rate of the deploy workflow over the last 30 days?
• › How many credits did the nightly workflow use last week?
• › Rerun the failed jobs in the last workflow on main

Questions

Is this an official CircleCI MCP server?

No. It is Memtro's MCP server with Memtro's CircleCI connector behind it: the connector reads CircleCI through its API with the credentials you connect on Dashboard → Connections, and CircleCI publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in CircleCI?

Only when you ask, and only what it has been granted: trigger a pipeline on a branch or tag (uses credits); rerun a workflow, or only its failed jobs (uses credits); cancel a running workflow or job; approve a job waiting on approval, such as a deploy; create, change or delete a scheduled pipeline; roll a deployed component back to an earlier version. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations

• GitHub MCP server
• AWS CloudWatch MCP server
• Sentry MCP server
• ServiceNow MCP server
• Okta MCP server
• Twilio MCP server