execute_code_file

Execute Python code files to run scripts and applications, enabling automated testing and program execution within a controlled environment.

Instructions

Execute an existing Python file. Use this as the final step after building up code with initialize_code_file and append_to_code_file.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file_path`	Yes	Full path to the Python file to execute

Implementation Reference

src/index.ts:159-198 (handler)

Core handler function that executes the Python code from the given file path using the configured environment, captures output and errors, and returns a structured JSON response.

async function executeCodeFromFile(filePath: string) {
    try {
        // Ensure file exists
        await access(filePath);

        // Get platform-specific command with unbuffered output
        const pythonCmd = platform() === 'win32' ? `python -u "${filePath}"` : `python3 -u "${filePath}"`;
        const { command, options } = getPlatformSpecificCommand(pythonCmd);

        // Execute code with unbuffered Python
        const { stdout, stderr } = await execAsync(command, {
            cwd: CODE_STORAGE_DIR,
            env: { ...process.env, PYTHONUNBUFFERED: '1' },
            ...options
        });

        const response = {
            status: stderr ? 'error' : 'success',
            output: stderr || stdout,
            file_path: filePath
        };

        return {
            type: 'text',
            text: JSON.stringify(response),
            isError: !!stderr
        };
    } catch (error) {
        const response = {
            status: 'error',
            error: error instanceof Error ? error.message : String(error),
            file_path: filePath
        };

        return {
            type: 'text',
            text: JSON.stringify(response),
            isError: true
        };
    }

src/index.ts:588-602 (registration)

Tool registration in the ListTools response, defining the name, description, and input schema.

{
    name: "execute_code_file",
    description: "Execute an existing Python file. Use this as the final step after building up code with initialize_code_file and append_to_code_file.",
    inputSchema: {
        type: "object",
        properties: {
            file_path: {
                type: "string",
                description: "Full path to the Python file to execute"
            }
        },
        required: ["file_path"]
    }
},
{

src/index.ts:705-707 (schema)
TypeScript interface defining the expected input arguments for the tool.
```
interface ExecuteCodeFileArgs {
    file_path?: string;
}
```

src/index.ts:826-841 (handler)

Dispatch handler within CallToolRequestSchema that validates input and invokes the core execution function.

case "execute_code_file": {
    const args = request.params.arguments as ExecuteCodeFileArgs;
    if (!args?.file_path) {
        throw new Error("File path is required");
    }

    const result = await executeCodeFromFile(args.file_path);

    return {
        content: [{
            type: "text",
            text: result.text,
            isError: result.isError
        }]
    };
}

MCP Code Executor