mcp-server-code-runner

Executes arbitrary code (Python, JavaScript, Bash, etc.) on a remote server through the Model Context Protocol, translating MCP tool calls into subprocess invocations with captured stdout/stderr/exit codes. Implements a standardized MCP server interface that exposes code execution as a callable tool, enabling Claude and other MCP clients to run code without direct shell access.

Automatically detects or accepts explicit language specifications (Python, JavaScript, Bash, Ruby, etc.) and routes code to the appropriate interpreter subprocess. Handles language-specific invocation patterns (e.g., 'python -c' for inline Python, 'node -e' for JavaScript) and manages interpreter availability checking before execution.

Captures stdout and stderr streams from spawned child processes in real-time, buffers the output, and returns it as structured data with exit codes. Handles stream encoding (UTF-8), manages buffer overflow scenarios, and provides both synchronous result collection and potential streaming callbacks for long-running processes.

Defines and registers code execution as an MCP tool with a standardized JSON schema that specifies input parameters (code, language, args) and output format. Implements the MCP tool protocol, allowing Claude and other MCP clients to discover the tool's capabilities, validate inputs against the schema, and invoke it with proper error handling.

Captures and reports execution errors including subprocess crashes, non-zero exit codes, timeout scenarios, and invalid language specifications. Returns structured error information (error type, message, exit code) that allows MCP clients to distinguish between different failure modes and respond appropriately.

Accepts command-line arguments as an array and passes them to the executed code, enabling parameterized code execution. Manages argument escaping and quoting to prevent injection attacks, and optionally isolates environment variables to prevent unintended side effects or information leakage.