
Shell Exec
Execute bash commands directly from Claude with support for background jobs. Run builds, file operations, system commands, and long-running processes.
Execute bash commands with background job support.
What it does
- Execute bash commands with optional timeout
- Run background jobs and processes
- Check status of running background jobs
- Perform file operations like find, grep, mv, rm
- Get system information with df, ps, env commands
- Run build tools like npm, make, or custom scripts
Best for
About Shell Exec
Shell Exec is a community-built MCP server published by domdomegg that provides AI assistants with tools and capabilities via the Model Context Protocol. Shell Exec - execute bash commands and manage background jobs on Linux. Fast, reliable shell command execution with back It is categorized under developer tools.
How to install
You can install Shell Exec in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
License
Shell Exec is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
shell-exec-mcp
MCP server for executing bash commands with background job support.
Use Cases
Run build commands: Execute npm run build, make, or other build tools and get the output.
File operations: Use find, grep, mv, rm, mkdir -p, stat etc. for file management.
Long-running tasks: Start servers or watch processes in background mode, check on them later.
System info: Run df -h, ps aux, env etc. to inspect the system state.
Setup
claude mcp add shell-exec-mcp -- npx -y shell-exec-mcp
Or with HTTP transport:
# Start the server
MCP_TRANSPORT=http PORT=3000 npx -y shell-exec-mcp
# Add to Claude
claude mcp add --transport http shell-exec-mcp http://localhost:3000/mcp
Tools
| Tool | Description |
|---|---|
execute | Run a bash command (with optional timeout and background mode) |
get_job_status | Check status of a background job |
Contributing
Pull requests are welcomed on GitHub! To get started:
- Install Git and Node.js
- Clone the repository
- Install dependencies with
npm install - Run
npm run testto run tests - Build with
npm run build
Releases
Versions follow the semantic versioning spec.
To release:
- Use
npm version <major | minor | patch>to bump the version - Run
git push --follow-tagsto push with tags - Wait for GitHub Actions to publish to the NPM registry.
Alternatives
Related Skills
Browse all skillsUse when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions.
"Expert in AppleScript and JavaScript for Automation (JXA) for macOS system scripting. Specializes in secure script execution, application automation, and system integration. HIGH-RISK skill due to shell command execution and system-wide control capabilities."
UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.
Bash Automated Testing System (BATS) for TDD-style testing of shell scripts. Use when: (1) Writing unit or integration tests for Bash scripts, (2) Testing CLI tools or shell functions, (3) Setting up test infrastructure with setup/teardown hooks, (4) Mocking external commands (curl, git, docker), (5) Generating JUnit reports for CI/CD, (6) Debugging test failures or flaky tests, (7) Implementing test-driven development for shell scripts.
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b