jenkins-mcp-server
Provides tools for managing Jenkins jobs, builds, console logs, queue, nodes, and plugins via the Jenkins REST API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@jenkins-mcp-server trigger a build for job 'backend/pipeline'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Jenkins MCP Server
A Model Context Protocol (MCP) server that exposes a Jenkins controller's REST
API to MCP-compatible clients such as Claude Desktop. Built on the
MCP Python SDK (1.27+,
protocol 2025-11-25) using FastMCP with httpx for async HTTP and
pydantic-settings for configuration.
Features
HTTP basic authentication using a Jenkins username + API token
Automatic CSRF crumb fetch and cache for POST requests
Works with nested folder job paths (
team/app/main)Tools for jobs, builds, console logs, queue, nodes and plugins
Related MCP server: MCP-Jenkins
Installation
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"Configuration
All configuration is read from environment variables prefixed with JENKINS_.
Variable | Default | Description |
|
| Base URL of the Jenkins controller |
| (empty) | Jenkins user for HTTP basic auth |
| (empty) | Jenkins API token (create in user settings) |
|
| Verify TLS certificates |
|
| HTTP timeout in seconds |
A .env file in the working directory is also picked up automatically.
Running
jenkins-mcpClaude Desktop configuration
Add an entry to claude_desktop_config.json:
{
"mcpServers": {
"jenkins": {
"command": "jenkins-mcp",
"env": {
"JENKINS_BASE_URL": "https://jenkins.example.com",
"JENKINS_USERNAME": "your-username",
"JENKINS_API_TOKEN": "your-api-token"
}
}
}
}Tools
Tool | Description |
| List jobs (optionally scoped to a folder) |
| Return full job metadata |
| Trigger a build, optionally with parameters |
| Return metadata for a specific build |
| Fetch the console text for a build |
| Stop a running build |
| List recent builds ( |
| List queued build items |
| Cancel a queue item by id |
| List Jenkins nodes / agents |
| List installed Jenkins plugins |
Development
Run tests with:
pytest -x --tb=shortLint with:
ruff check src testsAvailable Tools
11 toolscancel_queue_itemA
Cancel a queued build by its queue item id.
Inputs: item_id (required). Returns: object
get_buildB
Return detailed information about a specific build.
Inputs: job_name (required), build_number (required). Returns: object
get_build_logA
Return the plain-text console log for a build.
Inputs: job_name (required), build_number (required). Returns: result
get_jobA
Return full job metadata for job_name (supports nested folder paths).
Inputs: job_name (required). Returns: object
get_plugin_listA
Return all installed Jenkins plugins with metadata (depth=1).
Inputs: no named parameters. Returns: result
list_buildsA
Return up to limit recent builds for job_name with result/timestamp/duration.
Inputs: job_name (required), limit. Returns: result
list_jobsA
List Jenkins jobs. Optionally scoped to a folder path like team/app.
Inputs: folder. Returns: result
list_nodesA
Return all known Jenkins nodes/agents (including the built-in controller).
Inputs: no named parameters. Returns: result
list_queueA
Return all items currently in the Jenkins build queue.
Inputs: no named parameters. Returns: result
stop_buildC
Request cancellation of an in-progress build.
Inputs: job_name (required), build_number (required). Returns: object
trigger_buildA
Trigger a Jenkins build. Uses buildWithParameters when parameters is provided.
Inputs: job_name (required), parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool targets a distinct resource and action: jobs, builds, queue, nodes, plugins. Even the build-related tools (get_build, list_builds, get_build_log) are clearly separated by their specific purpose.
All tool names follow a consistent verb_noun pattern (list_, get_, trigger_, stop_, cancel_), with clear and predictable naming throughout.
With 11 tools, the set is well-scoped for a Jenkins MCP server, covering job management, build inspection, queue control, nodes, and plugins without unnecessary bloat.
The core lifecycle of inspecting and triggering builds is well covered. The main gap is lack of job creation/configuration tools, but those are often outside the typical read/trigger scope of such a server.
Maintenance
Related MCP Connectors
Host any HTTP API as a standard MCP server; auto-distribute to 12+ mainstream agent platforms.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables managing Jenkins operations like listing jobs, triggering builds, and checking build statuses through a configurable MCP server.310Apache 2.0
- AlicenseBqualityCmaintenanceA server that enables interaction with Jenkins CI/CD pipelines from any compatible MCP client (like Claude Desktop), allowing users to manage jobs, builds, coverage reports, and other Jenkins functionality through natural language.11500 npmMIT
- FlicenseNot gradedqualityFmaintenanceEnables LLMs to access Jenkins job data, trigger builds, and manage Jenkins tasks through a standardized interface.5-
- AlicenseNot gradedqualityCmaintenanceProvides Jenkins CI/CD integration for AI assistants through the Model Context Protocol, enabling job management, build control, and system administration via natural language commands.662 PyPI1MIT