Trace MCP

Instructions

Implementation Reference

• src/index.ts:311-329 (handler)

  MCP server handler for the 'extract_file' tool. Parses input, calls extractFromFile helper, and returns JSON-formatted schemas.

  case 'extract_file': {
    const input = ExtractFileInput.parse(args);
    log(`Extracting from file: ${input.filePath}`);
    
    const schemas = await extractFromFile(input.filePath);
    
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify({
            success: true,
            count: schemas.length,
            schemas,
          }, null, 2),
        },
      ],
    };
  }

• src/index.ts:65-67 (schema)

  Zod input schema for validating 'extract_file' tool arguments.

  const ExtractFileInput = z.object({
    filePath: z.string().describe('Path to a single TypeScript file to extract schemas from'),
  });

• src/index.ts:143-153 (registration)

  Tool registration in the MCP server's listTools response, including name, description, and JSON input schema.

  {
    name: 'extract_file',
    description: 'Extract MCP tool definitions from a single TypeScript file.',
    inputSchema: {
      type: 'object',
      properties: {
        filePath: { type: 'string', description: 'Path to a TypeScript file' },
      },
      required: ['filePath'],
    },
  },

• src/extract/index.ts:50-72 (helper)

  Main helper function implementing file-based schema extraction by delegating to language-specific parsers.

  export async function extractFromFile(filePath: string, language?: string): Promise<ProducerSchema[]> {
    // For backward compatibility, default to TypeScript
    const lang = language || 'typescript';
  
    if (!hasParser(lang)) {
      throw new Error(
        `No parser available for language: ${lang}. Make sure to call bootstrapLanguageParsers() at startup.`
      );
    }
  
    const parser = getParser(lang);
  
    // Extract from the directory containing the file
    const rootDir = filePath.substring(0, filePath.lastIndexOf('/') || filePath.lastIndexOf('\\'));
    const fileName = filePath.substring((filePath.lastIndexOf('/') || filePath.lastIndexOf('\\')) + 1);
  
    const allSchemas = await parser.extractSchemas({
      rootDir: rootDir || '.',
      include: [fileName],
    });
  
    return allSchemas.filter(s => s.location.file === filePath);
  }