Background Job Server
An MCP server that enables coding agents to execute and manage long-running shell commands asynchronously with capabilities for process monitoring, interaction, and lifecycle management.
What is Background Job Server?
Background Job Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that enables coding agents to execute and manage long-running shell commands asynchronously with capabilities for process monitoring, interaction, and lifecycle management.
An MCP server that enables coding agents to execute and manage long-running shell commands asynchronously with capabilities for process monitoring, interaction, and lifecycle management.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that enables coding agents to execute and mana
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-background-job-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Background Job Server
MCP Background Job Server is a Python MCP server that lets AI coding agents launch, monitor, and interact with long-running shell commands asynchronously. Instead of blocking while a build or test suite runs, agents can fire off a job, poll its output, send stdin input to interactive processes, and terminate jobs when done — all through a clean set of MCP tools.
Prerequisites
- Python 3.12 or newer
- uv package manager (recommended) or pip
- An MCP-compatible AI client such as Claude Desktop or Claude Code
- Shell access to the machine where background jobs will run
Install with uvx (recommended)
The simplest installation uses uvx, which downloads and runs the package in an isolated environment without a permanent install.
uvx mcp-background-jobInstall permanently with uv or pip
For a persistent install that survives shell sessions, use uv pip install or standard pip.
uv pip install mcp-background-job
# or
pip install mcp-background-jobConfigure environment variables (optional)
Set environment variables to control job limits, output buffer size, timeouts, and working directory. These can be set in the shell or passed directly in the MCP client config.
export MCP_BG_MAX_JOBS=10
export MCP_BG_MAX_OUTPUT_SIZE=10485760
export MCP_BG_JOB_TIMEOUT=3600
export MCP_BG_WORKING_DIR=/path/to/your/projectAdd the server to your MCP client config
Register the background job server with Claude Desktop or Claude Code. Using uvx ensures the latest version is always used without a separate install step.
Test the server with a simple job
Verify the setup by asking your AI client to run a simple shell command as a background job, check its status, and retrieve the output.
Background Job Server Examples
Client configuration
Claude Desktop configuration using uvx to run the MCP Background Job Server. Optionally pass environment variables to set working directory and job limits.
{
"mcpServers": {
"background-job": {
"command": "uvx",
"args": ["mcp-background-job"],
"env": {
"MCP_BG_MAX_JOBS": "10",
"MCP_BG_WORKING_DIR": "/path/to/your/project"
}
}
}
}Prompts to try
Use these prompts to manage background shell jobs through the AI agent.
- "Run 'npm run build' as a background job and tell me when it finishes"
- "Start 'npm run dev' in the background, then tail the last 20 lines of its output"
- "List all current background jobs and their statuses"
- "Send the string 'yes\n' to the interactive job with id job_001"
- "Kill the background job running pytest and show me its last 50 lines of output"Troubleshooting Background Job Server
uvx command not found
Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or see https://docs.astral.sh/uv/getting-started/installation/ for Windows. After installing, restart your terminal and MCP client.
Background jobs fail immediately with permission denied
Ensure the MCP_BG_WORKING_DIR directory exists and the user running the MCP server has execute permission. If using MCP_BG_ALLOWED_COMMANDS, verify your command matches one of the allowed regex patterns.
Job output is truncated or missing
Increase MCP_BG_MAX_OUTPUT_SIZE (default 10 MB per job). Use the tail tool with a specific line count rather than output to fetch only recent output. If the job completed and was cleaned up, output may no longer be available — decrease MCP_BG_CLEANUP_INTERVAL to keep jobs longer.
Frequently Asked Questions about Background Job Server
What is Background Job Server?
Background Job Server is a Model Context Protocol (MCP) server that mcp server that enables coding agents to execute and manage long-running shell commands asynchronously with capabilities for process monitoring, interaction, and lifecycle management. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Background Job Server?
Follow the installation instructions on the Background Job Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Background Job Server?
Background Job Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Background Job Server free to use?
Yes, Background Job Server is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Background Job Server Alternatives — Similar Developer Tools Servers
Looking for alternatives to Background Job Server? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Background Job Server in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Background Job Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.