CircleCI MCP Server — Hosted Devops Integration
MCP Server language Hosted language PublicMonitor pipelines, trigger builds, and manage workflows in CircleCI — give AI agents full CI/CD visibility.
Use with AI AssistantsMCP
Connect Claude, Cursor, or any MCP-compatible client — then call tools directly
① Add This MCP Server
Paste into your AI client config — then all its tools are available instantly.
{
"mcpServers": {
"circleci": {
"url": "https://mcp.aerostack.dev/s/aerostack/mcp-circleci",
"headers": {
"Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
}
}
}
}Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.
② Call a Tool
Ask your AI assistant to call a specific tool, or send raw JSON-RPC:
Natural Language Prompt
“Use the _ping tool to verify circleci token by fetching the current user. used internally by aerostack to validate credentials”
Using a Workspace?
Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.
description Overview
mcp-circleci — CircleCI MCP Server
Monitor pipelines, trigger builds, and manage CI/CD workflows in CircleCI.
CircleCI is a leading continuous integration and delivery platform. This MCP server gives your AI agents the ability to list pipelines, inspect workflow and job status, retrieve build artifacts, trigger new pipelines, and cancel running workflows — enabling automated CI/CD observability and control from any agent.
Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-circleci
What You Can Do
- Monitor pipeline status across projects — see which builds are passing, failing, or running
- Drill into workflow and job details to diagnose build failures without leaving your agent conversation
- Trigger new pipelines on specific branches with custom parameters for on-demand builds
- Cancel running workflows to stop wasted compute when a build is no longer needed
- Retrieve job artifacts (test reports, coverage files, binaries) programmatically
Setup
Step 1: Generate a CircleCI Personal API Token
- Go to circleci.com and log in
- Click your avatar (bottom-left) → User Settings → Personal API Tokens
- Click Create New Token, give it a name (e.g., "Aerostack MCP"), and copy the token
Step 2: Add to Aerostack Workspace
- Go to your Aerostack workspace → Add Server → search "CircleCI"
- Paste your
CIRCLECI_TOKENwhen prompted - Click Test to verify the connection
Available Tools
| Tool | Description |
|---|---|
_ping |
Verify token by fetching the current user |
list_pipelines |
List recent pipelines for a project |
get_pipeline |
Get details of a single pipeline |
list_workflows |
List workflows for a pipeline |
get_workflow |
Get details of a single workflow |
list_jobs |
List jobs for a workflow |
get_job |
Get details of a job by job number |
get_job_artifacts |
List artifacts produced by a job |
trigger_pipeline |
Trigger a new pipeline on a project |
cancel_workflow |
Cancel a running workflow |
Configuration
| Variable | Required | Description |
|---|---|---|
CIRCLECI_TOKEN |
Yes | CircleCI Personal API Token |
Project Slugs
CircleCI identifies projects using a slug format: {vcs}/{org}/{repo}
- GitHub:
gh/my-org/my-repo - Bitbucket:
bb/my-org/my-repo
Use this format for project_slug parameters in all tools.
Example Prompts
"List the last 5 pipelines for gh/acme/api-server and tell me if any are failing"
"Show me the jobs in the most recent workflow for pipeline abc-123 and check if tests passed"
"Trigger a new pipeline on the staging branch of gh/acme/api-server"
"Cancel workflow xyz-789 — we pushed a fix and need to re-run"
"Get the test artifacts from job 542 in gh/acme/api-server"
Direct API Call
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-circleci \
-H 'Content-Type: application/json' \
-H 'X-Mcp-Secret-CIRCLECI-TOKEN: your-circleci-token' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_pipelines","arguments":{"project_slug":"gh/my-org/my-repo"}}}'
License
MIT
terminal Tools (10)
Available tools on this MCP server. Each tool can be called directly from any AI agent.
_ping #1 Verify CircleCI token by fetching the current user. Used internally by Aerostack to validate credentials.
list_pipelines #2 List recent pipelines for a project (org-name/repo-name on a VCS)
get_pipeline #3 Get details of a single pipeline by its ID
list_workflows #4 List workflows for a given pipeline
get_workflow #5 Get details of a single workflow by its ID
list_jobs #6 List jobs for a given workflow
get_job #7 Get details of a single job by its job number within a project
get_job_artifacts #8 List artifacts produced by a job
trigger_pipeline #9 Trigger a new pipeline for a project, optionally on a specific branch with parameters
cancel_workflow #10 Cancel a running workflow
Details
language Live Endpoint
https://mcp.aerostack.dev/s/aerostack/mcp-circleci
Sub-50ms globally · Zero cold start
Publisher
Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.
More in Devops
Browse Devops MCPs →Asana Project Management
by @aerostack
Tasks, projects, sections, comments, teams, custom fields via Asana's official MCP
Atlassian Cloud
by @aerostack
Jira issues, sprints, Confluence pages via Atlassian's official MCP
Cloudflare Platform
by @aerostack
Cloudflare Workers, KV, R2, D1, Pages, DNS via Cloudflare's official MCP
Datadog Observability
by @aerostack
Dashboards, monitors, logs, metrics, incidents, SLOs, APM traces via Datadog's official MCP
Figma Design
by @aerostack
Files, frames, components, comments, variables via Figma's official MCP
GitHub API
by @aerostack
GitHub repos, PRs, issues, branches, code search via GitHub's official hosted MCP
Frequently asked questions
What is the CircleCI MCP server and what can it do? +
The CircleCI MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `list_pipelines`, `get_pipeline`, `list_workflows`, `get_workflow`. You get one hosted URL — no self-hosting — that works from Claude, Cursor, ChatGPT, Gemini, VS Code, or any MCP-compatible client, and you can share it with your team or combine it with other MCP servers in a workspace.
Is the CircleCI MCP server hosted, or do I have to run it myself? +
It's hosted on Aerostack's edge infrastructure — you don't deploy or maintain anything. Add it to a workspace and you get one authenticated URL, with secrets encrypted, that any AI agent or editor can connect to. Use it solo or share the same URL across your whole team.
Which AI agents and editors can use the CircleCI MCP server? +
Any MCP client: Claude and Claude Code, Cursor, ChatGPT, Gemini, Windsurf, Cline, VS Code, and custom agents. Because it's one hosted URL, the same CircleCI MCP server works everywhere — and you can compose it with other MCP servers, skills, and functions behind a single workspace URL.
How do I install the CircleCI MCP server in Claude Desktop? +
Add the following to your Claude Desktop config (`claude_desktop_config.json`): ```json { "mcpServers": { "@aerostack/mcp-circleci": { "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-circleci"] } } } ``` Then restart Claude Desktop and the tools will appear automatically.
How do I use the CircleCI MCP server in Cursor? +
In Cursor, open **Settings → MCP** and add: ```json { "name": "@aerostack/mcp-circleci", "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-circleci"] } ``` Save and reload Cursor. The MCP tools will be available in Agent mode.
Does CircleCI MCP require authentication? +
Yes. CircleCI requires authentication. Check the MCP's documentation for the required credentials.