jenkins
MCP server for Jenkins CI/CD - Intelligent automation server integration for GenAI
claude mcp add --transport stdio lokimcpuniverse-jenkins-mcp-server python -m jenkins_mcp.server \ --env JENKINS_URL="https://jenkins.example.com" \ --env JENKINS_TIMEOUT="30" \ --env JENKINS_USERNAME="your_username" \ --env JENKINS_API_TOKEN="your_api_token" \ --env JENKINS_VERIFY_SSL="true" \ --env JENKINS_MAX_RETRIES="3"
How to use
This Jenkins MCP Server enables GenAI-powered interaction with a Jenkins automation environment. It exposes a comprehensive set of tools for managing Jenkins jobs, pipelines, builds, queues, nodes, plugins, and credentials through the MCP protocol, allowing AI agents to list, create, trigger, monitor, and retrieve information from Jenkins. You can configure multiple Jenkins masters (via the advanced configuration section) and run the MCP server to enable Claude/Desktop or other MCP clients to issue tool calls against Jenkins. The included tools cover core Jenkins operations such as listing jobs, creating or retrieving job configurations, triggering builds with parameters, reading build status and logs, managing pipelines, and handling credentials and plugins. Authentication can be performed using API tokens, username/password, OAuth, or LDAP/AD, depending on your Jenkins setup. To start, install the Python package and run the MCP server component; then configure your MCP client with the provided environment variables (URL, credentials) so the server can connect to Jenkins securely.
How to install
Prerequisites:
- Python 3.8+ installed on your machine
- Internet access to install Python packages
Install the MCP server package from PyPI:
pip install jenkins-mcp-server
Or clone the repository and install in editable mode:
git clone https://github.com/asklokesh/jenkins-mcp-server.git
cd jenkins-mcp-server
pip install -e .
Run the MCP server (example using the recommended CLI entry point):
# Basic run (adjust environment variables as needed)
export JENKINS_URL="https://jenkins.example.com"
export JENKINS_USERNAME="your_username"
export JENKINS_API_TOKEN="your_api_token"
python -m jenkins_mcp.server
Alternatively, use your MCP client configuration (Claude/Desktop) as shown in the README snippet to point to the server and pass credentials via environment variables.
Additional notes
Environment variables are required to connect to Jenkins and should be kept secure. Ensure SSL verification is enabled in production (JENKINS_VERIFY_SSL=true) and set appropriate timeouts and retry policies. If you run multiple Jenkins masters, consider using the Multi-Master configuration to segment credentials and URLs per master. The MCP server supports API token, username/password, OAuth 2.0, and LDAP/AD authentication depending on your Jenkins setup. If you encounter connectivity issues, verify network access to JENKINS_URL and confirm that the provided credentials have sufficient privileges for the requested operations. For Claude/Desktop integration, mirrors of the examples used in the README can be adapted for your environment.
Related MCP Servers
ai-dev-tools-zoomcamp
AI Dev Tools Zoomcamp is a free course that helps you use AI tools to write better code, faster. We're starting the first cohort of this course on November 18, 2025! Sign up here to join us 👇🏼
jenkins -enterprise
The most advanced Jenkins MCP server available - Enterprise debugging, multi-instance management, AI-powered failure analysis, vector search, and configurable diagnostics for complex CI/CD pipelines.
salesforce
MCP server for Salesforce API integration - Complete CRM integration for GenAI applications
rancher
MCP server for Rancher - Kubernetes management and deployment platform
argocd
MCP server for ArgoCD - GitOps continuous delivery for Kubernetes with GenAI
git
MCP server from LokiMCPUniverse/git-mcp-server