mcpField
R
rundeck-mcp-server

rundeck-mcp-server

Local
github.com/mariomorenodevCloud & Infra1Updated 26w ago

About rundeck-mcp-server

rundeck-mcp-server connects MCP-compatible assistants and clients to Rundeck for job and infrastructure operations. Its tools cover project and job management, execution monitoring, nodes, secrets, webhooks, access policies, and system status.

Key features

  1. 01Project and job CRUD and configuration
  2. 02Run, retry, and schedule jobs
  3. 03Monitor executions and inspect logs
  4. 04Browse nodes and manage key storage
  5. 05Manage webhooks, ACL policies, and system status

Use cases

  1. 01Run or retry a deployment job
  2. 02Check running executions and read logs
  3. 03Find nodes using filter expressions
  4. 04Review Rundeck health and access policies

MCP support

Exposes Rundeck operations as MCP tools for compatible clients. It connects to a configured Rundeck instance using its URL and API token.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"mariomorenodev-rundeck": {
"command": "npx",
"args": [
"-y",
"rundeck-mcp-server"
],
"env": {
"RUNDECK_URL": "<RUNDECK_URL>",
"RUNDECK_API_TOKEN": "<RUNDECK_API_TOKEN>",
"RUNDECK_API_VERSION": "<RUNDECK_API_VERSION>",
"RUNDECK_TIMEOUT": "<RUNDECK_TIMEOUT>"
}
}
}
}
Run commandnpx -y rundeck-mcp-server
Environment variables to set
RUNDECK_URLRundeck server URL (e.g., http://localhost:4440)
RUNDECK_API_TOKENSecretAPI token for authentication
RUNDECK_API_VERSIONRundeck API version (default: 41)
RUNDECK_TIMEOUTRequest timeout in milliseconds (default: 30000)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmrundeck-mcp-server1.0.3

Tools

50

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

rundeck-mcp-server

npm version License

The most comprehensive MCP (Model Context Protocol) server for Rundeck. Manage jobs, executions, projects, nodes, and more from Claude, Cursor, or any MCP-compatible client.

50 tools across 7 domains — full CRUD operations, execution monitoring, and system management.

Features

  • Projects — List, create, delete, and configure projects
  • Jobs — List, create, run, retry, import/export, enable/disable execution and scheduling
  • Executions — Monitor running jobs, get logs, abort executions, query history
  • Nodes — Browse node inventory with filter expressions
  • System — Server info, health checks, metrics, execution mode control
  • Key Storage — Manage secrets, passwords, and SSH keys
  • Webhooks — Create and manage webhook triggers
  • ACL Policies — Full CRUD for system access control policies

Quick Start

Prerequisites
Using with Claude Code

Add to your MCP settings:

{
  "mcpServers": {
    "rundeck": {
      "command": "npx",
      "args": ["-y", "rundeck-mcp-server"],
      "env": {
        "RUNDECK_URL": "http://your-rundeck-server:4440",
        "RUNDECK_API_TOKEN": "your-api-token"
      }
    }
  }
}
Using with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "rundeck": {
      "command": "npx",
      "args": ["-y", "rundeck-mcp-server"],
      "env": {
        "RUNDECK_URL": "http://your-rundeck-server:4440",
        "RUNDECK_API_TOKEN": "your-api-token"
      }
    }
  }
}
Using with Cursor

Add to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "rundeck": {
      "command": "npx",
      "args": ["-y", "rundeck-mcp-server"],
      "env": {
        "RUNDECK_URL": "http://your-rundeck-server:4440",
        "RUNDECK_API_TOKEN": "your-api-token"
      }
    }
  }
}

Configuration

Environment VariableRequiredDefaultDescription
RUNDECK_URLYes—Rundeck server URL (e.g., http://localhost:4440)
RUNDECK_API_TOKENYes—API token for authentication
RUNDECK_API_VERSIONNo41Rundeck API version
RUNDECK_TIMEOUTNo30000Request timeout in milliseconds

Available Tools

Projects (6 tools)
ToolDescription
rundeck_list_projectsList all projects
rundeck_get_projectGet project details and configuration
rundeck_create_projectCreate a new project
rundeck_delete_projectDelete a project permanently
rundeck_get_project_configGet project configuration properties
rundeck_set_project_configUpdate project configuration
Jobs (14 tools)
ToolDescription
rundeck_list_jobsList jobs with filtering by group, name, tags
rundeck_get_jobGet full job definition (steps, options, schedule)
rundeck_get_job_metadataGet job metadata (author, dates)
rundeck_run_jobExecute a job with options and node filters
rundeck_retry_jobRetry a failed execution
rundeck_import_jobsImport jobs from JSON/YAML/XML
rundeck_export_jobsExport job definitions
rundeck_delete_jobDelete a job
rundeck_bulk_delete_jobsDelete multiple jobs at once
rundeck_enable_job_executionEnable job execution
rundeck_disable_job_executionDisable job execution
rundeck_enable_job_scheduleEnable job scheduling
rundeck_disable_job_scheduleDisable job scheduling
rundeck_get_job_forecastGet upcoming scheduled execution times
Executions (8 tools)
ToolDescription
rundeck_list_executionsQuery executions with status and time filters
rundeck_list_running_executionsList currently running executions
rundeck_get_executionGet execution details (status, duration, nodes)
rundeck_get_execution_outputGet execution log output
rundeck_abort_executionAbort a running execution
rundeck_get_job_executionsList execution history for a job
rundeck_delete_job_executionsDelete all executions for a job
rundeck_bulk_delete_executionsDelete multiple executions by ID
Nodes (2 tools)
ToolDescription
rundeck_list_nodesList nodes with filter expressions
rundeck_get_nodeGet node details
System (12 tools)
ToolDescription
rundeck_system_infoServer version, uptime, and system stats
rundeck_get_execution_modeCheck active/passive execution mode
rundeck_set_execution_modeEnable or disable executions system-wide
rundeck_get_metricsServer performance metrics
rundeck_healthcheckSystem health check
rundeck_list_usersList all users
rundeck_get_log_storageLog storage status
rundeck_list_acl_policiesList ACL policy files
rundeck_get_acl_policyGet ACL policy content
rundeck_create_acl_policyCreate ACL policy
rundeck_update_acl_policyUpdate ACL policy
rundeck_delete_acl_policyDelete ACL policy
Key Storage (4 tools)
ToolDescription
rundeck_list_keysBrowse key storage tree
rundeck_get_key_metadataGet key metadata (not the secret value)
rundeck_create_keyStore a password, public key, or private key
rundeck_delete_keyDelete a stored key
Webhooks (4 tools)
ToolDescription
rundeck_list_webhooksList webhooks in a project
rundeck_get_webhookGet webhook details
rundeck_create_webhookCreate a webhook trigger
rundeck_delete_webhookDelete a webhook

Usage Examples

Once configured, you can interact with Rundeck using natural language:

  • "List all projects in Rundeck"
  • "Show me the running executions in the production project"
  • "Run the deploy-app job in the staging project with version=2.1.0"
  • "Get the logs from execution 1234"
  • "Abort execution 5678"
  • "Show me all failed executions in the last 24 hours"
  • "List the nodes tagged as 'web' in the production project"
  • "Check the Rundeck server health"
  • "Disable the cleanup job schedule"

Development

# Clone the repository
git clone https://github.com/mariomorenodev/rundeck-mcp-server.git
cd rundeck-mcp-server

# Install dependencies
npm install

# Build
npm run build

# Run in development mode
RUNDECK_URL=http://localhost:4440 RUNDECK_API_TOKEN=your-token npm run dev

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the Apache License 2.0 — see the LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.