MCP File Context Server

Instructions

Implementation Reference

• src/index.ts:1375-1426 (handler)

  The handler function that implements the getFiles tool logic. It processes a list of file paths, validates access, reads content and metadata for each, handles errors per file, and returns JSON with file contents and metadata.
  private async handleGetFiles(args: any) { const { filePathList } = args; await this.loggingService.debug('Getting files', { fileCount: filePathList?.length || 0, operation: 'get_files' }); if (!Array.isArray(filePathList)) { throw new McpError(ErrorCode.InvalidParams, 'filePathList must be an array'); } const results: any[] = []; // Process each file, handling errors gracefully for (const fileItem of filePathList) { const filePath = fileItem.fileName; try { // PATTERN: Use existing security validation const resolvedPath = await this.validateAccess(filePath); // PATTERN: Use existing file reading methods const metadata = await this.getFileMetadata(resolvedPath); const { content } = await this.readFileWithEncoding(resolvedPath, 'utf8'); // TRANSFORM: Match required response schema results.push({ fileName: filePath, content: content, fileSize: metadata.size, lastModifiedDateTime: metadata.modifiedTime }); } catch (error) { // GOTCHA: Don't fail entire request - log error and continue await this.loggingService.error('Error reading file', error as Error, { filePath, operation: 'get_files' }); // Include error info in response but continue processing results.push({ fileName: filePath, content: `Error: ${error instanceof Error ? error.message : 'Unknown error'}`, fileSize: 0, lastModifiedDateTime: new Date().toISOString() }); } } // PATTERN: Use existing response format method return this.createJsonResponse(results); }
• src/index.ts:1560-1583 (schema)

  The input schema definition for the getFiles tool, specifying an array of file objects with fileName property.
  name: 'getFiles', description: 'Retrieve multiple files by their paths, returning content and metadata for each file', inputSchema: { type: 'object', properties: { filePathList: { type: 'array', description: 'The list of file paths for the file content to return.', minItems: 1, items: { type: 'object', properties: { fileName: { type: 'string', description: 'Path and file name for the file to be retrieved.' } }, required: ['fileName'] } } }, required: ['filePathList'] } }
• src/index.ts:1619-1621 (registration)

  Registration of the getFiles handler in the CallToolRequestSchema switch statement.
  case 'getFiles': return await this.handleGetFiles(request.params.arguments); default:
• src/index.ts:1441-1585 (registration)

  Registration of the getFiles tool in the ListToolsRequestSchema response, including name, description, and schema.
  tools: [ { name: 'read_context', description: 'Read and analyze code files with advanced filtering and chunking. The server automatically ignores common artifact directories and files:\n- Version Control: .git/\n- Python: .venv/, __pycache__/, *.pyc, etc.\n- JavaScript/Node.js: node_modules/, bower_components/, .next/, dist/, etc.\n- IDE/Editor: .idea/, .vscode/, .env, etc.\n\nFor large files or directories, use get_chunk_count first to determine total chunks, then request specific chunks using chunkNumber parameter.', inputSchema: { type: 'object', properties: { path: { type: 'string', description: 'Path to file or directory to read' }, maxSize: { type: 'number', description: 'Maximum file size in bytes. Files larger than this will be chunked.', default: 1048576 }, encoding: { type: 'string', description: 'File encoding (e.g., utf8, ascii, latin1)', default: 'utf8' }, recursive: { type: 'boolean', description: 'Whether to read directories recursively (includes subdirectories)', default: true }, fileTypes: { type: ['array', 'string'], items: { type: 'string' }, description: 'File extension(s) to include WITHOUT dots (e.g. ["ts", "js", "py"] or just "ts"). Empty/undefined means all files.', default: [] }, chunkNumber: { type: 'number', description: 'Which chunk to return (0-based). Use with get_chunk_count to handle large files/directories.', default: 0 } }, required: ['path'] } }, { name: 'get_chunk_count', description: 'Get the total number of chunks that will be returned for a read_context request.\nUse this tool FIRST before reading content to determine how many chunks you need to request.\nThe parameters should match what you\'ll use in read_context.', inputSchema: { type: 'object', properties: { path: { type: 'string', description: 'Path to file or directory' }, encoding: { type: 'string', description: 'File encoding (e.g., utf8, ascii, latin1)', default: 'utf8' }, maxSize: { type: 'number', description: 'Maximum file size in bytes. Files larger than this will be chunked.', default: 1048576 }, recursive: { type: 'boolean', description: 'Whether to read directories recursively (includes subdirectories)', default: true }, fileTypes: { type: ['array', 'string'], items: { type: 'string' }, description: 'File extension(s) to include WITHOUT dots (e.g. ["ts", "js", "py"] or just "ts"). Empty/undefined means all files.', default: [] } }, required: ['path'] } }, { name: 'set_profile', description: 'Set the active profile for context generation', inputSchema: { type: 'object', properties: { profile_name: { type: 'string', description: 'Name of the profile to activate' } }, required: ['profile_name'] } }, { name: 'get_profile_context', description: 'Get repository context based on current profile settings', inputSchema: { type: 'object', properties: { refresh: { type: 'boolean', description: 'Whether to refresh file selection before generating context', default: false } } } }, { name: 'generate_outline', description: 'Generate a code outline for a file, showing its structure (classes, functions, imports, etc). Supports TypeScript/JavaScript and Python files.', inputSchema: { type: 'object', properties: { path: { type: 'string', description: 'Path to the file to analyze' } }, required: ['path'] } }, { name: 'getFiles', description: 'Retrieve multiple files by their paths, returning content and metadata for each file', inputSchema: { type: 'object', properties: { filePathList: { type: 'array', description: 'The list of file paths for the file content to return.', minItems: 1, items: { type: 'object', properties: { fileName: { type: 'string', description: 'Path and file name for the file to be retrieved.' } }, required: ['fileName'] } } }, required: ['filePathList'] } } ] }));