MCP Jenkins

PyPI Version License

The Model Context Protocol (MCP) is an open-source implementation that bridges Jenkins with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Jenkins tools while maintaining data privacy and security.

Cursor Demo

cursor demo

Setup Guide

Installation

Choose one of these installation methods:

# Using uv (recommended)
pip install uv
uvx mcp-jenkins

# Using pip
pip install mcp-jenkins

# Using Smithery
npx -y @smithery/cli@latest install @lanbaoshen/mcp-jenkins --client claude

Docker Installation

Pull the latest image from GitHub Container Registry:

docker pull ghcr.io/lanbaoshen/mcp-jenkins:latest

Configuration and Usage

Cursor

Open Cursor Settings
Navigate to MCP
Click + Add new global MCP server

This will create or edit the ~/.cursor/mcp.json file with your MCP server configuration.

{
  "mcpServers": {
    "mcp-jenkins": {
      "command": "uvx",
      "args": [
        "mcp-jenkins",
        "--jenkins-url=xxx",
        "--jenkins-username=xxx",
        "--jenkins-password=xxx"
      ]
    }
  }
}

Note: You can set your Jenkins token to password too!

VSCode Copilot Chat

Create .vscode folder with mcp.json file in you workspace for local setup or edit settings.json trough settings menù.
Insert the following configuration:

Option 1: Using HTTP Headers (Recommended)

Pass Jenkins credentials directly via HTTP headers in the mcp.json configuration. This method leverages FastMCP's ASGI middleware to securely extract credentials from HTTP request headers.

SSE mode

{
    "servers": {
        "jenkins": {
            "url": "http://localhost:3000/sse",
            "type": "sse",
            "headers": {
                "x-jenkins-url": "https://your-jenkins-server.com",
                "x-jenkins-username": "your-username",
                "x-jenkins-password": "your-api-token"
            }
        }
    }
}

Streamable-Http mode (Recommended)

{
    "servers": {
        "mcp-jenkins": {
            "autoApprove": [],
            "disabled": false,
            "timeout": 60,
            "type": "streamableHttp",
            "url": "http://localhost:3000/mcp",
            "headers": {
                "x-jenkins-url": "https://your-jenkins-server.com",
                "x-jenkins-username": "your-username",
                "x-jenkins-password": "your-api-token"
            }
        }
    }
}

Then start the MCP server without credentials (they'll be automatically extracted from headers):

# For SSE transport
uvx mcp-jenkins --transport sse --port 3000

# For streamable-http transport  
uvx mcp-jenkins --transport streamable-http --port 3000

Option 2: Using CLI Arguments (Traditional Method)

Pass credentials when starting the server:

SSE mode

{
    "servers": {
        "jenkins": {
            "url": "http://localhost:9887/sse",
            "type": "sse"
        }
    }
}

Streamable-Http mode

{
    "servers": {
        "mcp-jenkins": {
            "autoApprove": [],
            "disabled": false,
            "timeout": 60,
            "type": "streamableHttp",
            "url": "http://localhost:9887/mcp"
        }
    }
}

Start the server (credentials will be read from environment variables):

uvx mcp-jenkins --transport sse --port 3000
# or
uvx mcp-jenkins --transport streamable-http --port 3000

Option 3: Using CLI Arguments (Sets Environment Variables)

Pass credentials as command-line arguments. These will be set as environment variables for the server process:

uvx mcp-jenkins \
  --jenkins-url https://your-jenkins-server.com \
  --jenkins-username your_username  \
  --jenkins-password your_password_or_token \
  --transport sse --port 9887

line arguments

# Stdio Mode
uvx mcp-jenkins --jenkins-url xxx --jenkins-username xxx --jenkins-password xxx --read-only

# SSE Mode
uvx mcp-jenkins --jenkins-url xxx --jenkins-username xxx --jenkins-password xxx --transport sse --port 9887

# Streamable-Http Mode
uvx mcp-jenkins --jenkins-url xxx --jenkins-username xxx --jenkins-password xxx --transport streamable-http --port 9887

AutoGen

Install and exec

Install autogen:

pip install "autogen-ext[azure,ollama,openai,mcp]" autogen-chat

Run python scripts:

import asyncio

from autogen_ext.tools.mcp import StdioMcpToolAdapter, StdioServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_core import CancellationToken


async def main() -> None:
    # Create server params for the remote MCP service
    server_params = StdioServerParams(
        command='uvx',
        args=[
            'mcp-jenkins',
            '--jenkins-username',
            'xxx',
            '--jenkins-password',
            'xxx',
            '--jenkins-url',
            'xxx'
        ],
    )

    # Get the translation tool from the server
    adapter = await StdioMcpToolAdapter.from_server_params(server_params, 'get_all_jobs')

    # Create an agent that can use the translation tool
    agent = AssistantAgent(
        name='jenkins_assistant',
        model_client=[Replace_with_your_model_client],
        tools=[adapter],
    )

    # Let the agent translate some text
    await Console(
        agent.run_stream(task='Get all jobs', cancellation_token=CancellationToken())
    )


if __name__ == "__main__":
    asyncio.run(main())

Available Tools

Tool	Description
get_all_jobs	Get all jobs
get_job_config	Get job config
search_jobs	Search job by specific field
get_running_builds	Get running builds
stop_build	Stop running build
get_build_info	Get build info
get_build_sourcecode	Get the pipeline source code of a specific build in Jenkins
get_job_info	Get job info
build_job	Build a job with param
get_build_logs	Get build logs
get_test_results	Get test results for a specific build
get_all_nodes	Get nodes
get_node_config	Get the config of node
get_all_queue_items	Get all queue items
get_queue_item	Get queue item info
cancel_queue_item	Cancel queue item
get_multibranch_jobs	Get all multibranch pipeline jobs from Jenkins, optionally filtered by patterns
get_multibranch_branches	Get all branches for a specific multibranch pipeline job
scan_multibranch_pipeline	Trigger a scan of a multibranch pipeline to discover new branches

Development & Debugging

# Using MCP Inspector
# For installed package
npx @modelcontextprotocol/inspector uvx mcp-jenkins --jenkins-url xxx --jenkins-username xxx --jenkins-password xxx

# For local development version
npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-jenkins run mcp-jenkins --jenkins-url xxx --jenkins-username xxx --jenkins-password xxx

Pre-Commit Hook

# Install Dependency
uv sync --all-extras --dev
pre-commit install

# Manually execute
pre-commit run --all-files

UT

# Install Dependency
uv sync --all-extras --dev

# Execute UT
uv run pytest --cov=mcp_jenkins

License

Licensed under MIT - see LICENSE file. This is not an official Jenkins product.

mcp-jenkins