Code Sandbox MCP Server

Instructions

Implementation Reference

• src/code_sandbox_mcp/server.py:43-62 (handler)

  The @mcp.tool() decorated function serving as both the handler and registration for the 'run_javascript_code' tool. It validates input via Annotated Field, executes the code using the run_code helper with language='javascript', handles output and errors, and returns TextContent.
  @mcp.tool() def run_javascript_code( code: Annotated[ str, Field( description=f"The JavaScript code to execute, included libraries are {DEFAULT_ENVIRONMENT_MAP['javascript']['installed_libraries']}", ), ], ) -> TextContent: """Execute JavaScript code in the sandbox environment and captures the standard output and error.""" try: result = run_code(code, language="javascript") if len(result) == 0: result = ExecutionResult( exit_code=1, stderr="No output, forgot console.logs?" ).to_json() return TextContent(text=result, type="text") except Exception as e: result = ExecutionResult(exit_code=1, stderr=str(e)).to_json() return TextContent(text=result, type="text")
• src/code_sandbox_mcp/utils.py:25-78 (helper)

  Core helper function run_code that performs the actual code execution in a secure sandbox using llm_sandbox.SandboxSession, configured for the specified language (including 'javascript'), handling environment setup, libraries, and timeouts.
  def run_code( code: str, language: Literal["python", "javascript"] = DEFAULT_LANGUAGE, image: str | None = None, libraries: list[str] | None = None, timeout: int = EXECUTION_TIMEOUT, ) -> str: """Execute code in a secure sandbox environment and automatic visualization capture. Args: code: The code to execute language: Programming language (python, javascript, go) libraries: List of libraries/packages to install image: Docker image to use for the sandbox session timeout: Execution timeout in seconds (default: 30) Returns: List of content items including execution results and any generated visualizations """ if language not in DEFAULT_ENVIRONMENT_MAP: raise ValueError(f"Language {language} not supported") session_args = { "lang": language, "keep_template": True, "verbose": VERBOSE, "backend": _get_backend(), "session_timeout": timeout, "image": DEFAULT_ENVIRONMENT_MAP[language]["image"], } if os.getenv("PASSTHROUGH_ENV", None): env_vars = {} for var in os.getenv("PASSTHROUGH_ENV", None).split(","): env_vars[var] = os.getenv(var) session_args["runtime_configs"] = {"environment": env_vars} if os.getenv("CONTAINER_IMAGE", None) and os.getenv("CONTAINER_LANGUAGE", None): session_args["lang"] = os.getenv("CONTAINER_LANGUAGE") session_args["image"] = os.getenv("CONTAINER_IMAGE") if libraries: session_args["libraries"] = libraries with SandboxSession(**session_args) as session: result = session.run( code=code, libraries=libraries or [], timeout=timeout, ) if result.exit_code != 0: raise Exception(result.stderr.strip()) return result.stdout.strip()
• src/code_sandbox_mcp/server.py:45-50 (schema)

  Pydantic-based input schema definition for the tool, specifying the 'code' parameter as a string with description of supported JavaScript libraries.
  code: Annotated[ str, Field( description=f"The JavaScript code to execute, included libraries are {DEFAULT_ENVIRONMENT_MAP['javascript']['installed_libraries']}", ), ],
• src/code_sandbox_mcp/server.py:43-43 (registration)

  The @mcp.tool() decorator registers the run_javascript_code function as an MCP tool.
  @mcp.tool()