MCP Python Interpreter

Instructions

Install a Python package in the specified environment.

Args:
    package_name: Name of the package to install
    environment: Name of the Python environment
    upgrade: Whether to upgrade if already installed
    timeout: Maximum execution time in seconds

Implementation Reference

• mcp_python_interpreter/server.py:684-720 (handler)

  The handler function implementing the 'install_package' MCP tool. It uses pip to install or upgrade the specified package in the chosen Python environment via subprocess execution. Includes input validation for environments and error handling.

  @mcp.tool()
  async def install_package(
      package_name: str,
      environment: str = "default",
      upgrade: bool = False,
      timeout: int = 300
  ) -> str:
      """
      Install a Python package in the specified environment.
      
      Args:
          package_name: Name of the package to install
          environment: Name of the Python environment
          upgrade: Whether to upgrade if already installed
          timeout: Maximum execution time in seconds
      """
      environments = get_python_environments()
      
      if environment == "default" and not any(e["name"] == "default" for e in environments):
          environment = "system"
          
      env = next((e for e in environments if e["name"] == environment), None)
      if not env:
          return f"Environment '{environment}' not found. Available: {', '.join(e['name'] for e in environments)}"
      
      cmd = [env["path"], "-m", "pip", "install"]
      if upgrade:
          cmd.append("--upgrade")
      cmd.append(package_name)
      
      result = await run_subprocess_async(cmd, timeout=timeout)
      
      if result["status"] == 0:
          return f"Successfully {'upgraded' if upgrade else 'installed'} {package_name} in {environment}."
      else:
          return f"Error installing {package_name}:\n{result['stderr']}"