document_reader
Extract text content from PDF, DOCX, TXT, HTML, and CSV files by specifying the file path, enabling document analysis and processing.
Instructions
Read content from non-image document-files at specified paths, supporting various file formats: .pdf, .docx, .txt, .html, .csv
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the file to be read |
Implementation Reference
- src/tools/documentReader.ts:83-118 (handler)Core handler function that executes the document reading logic by determining file type and calling appropriate reader, returning success/data or error.
export async function readFile(filePath: string) { try { const ext = path.extname(filePath).toLowerCase(); let content: string; switch (ext) { case ".pdf": content = await readPDFFile(filePath); break; case ".docx": content = await readDocxFile(filePath); break; case ".txt": content = await readTextFile(filePath); break; case ".html": content = await readHTMLFile(filePath); break; case ".csv": content = await readCSVFile(filePath); break; default: throw new Error(`Unsupported file format: ${ext}`); } return { success: true, data: content, }; } catch (error) { return { success: false, error: error instanceof Error ? error.message : "Unknown error", }; } } - src/index.ts:59-75 (handler)MCP server request handler dispatch for 'document_reader' tool: validates input, calls readFile, formats response.
if (name === "document_reader") { if (!isFileReaderArgs(args)) { throw new Error("Invalid arguments for document_reader"); } const result = await readFile(args.filePath); if (!result.success) { return { content: [{ type: "text", text: `Error: ${result.error}` }], isError: true, }; } return { content: [{ type: "text", text: result.data }], isError: false, }; } - src/tools/documentReader.ts:9-23 (schema)Tool definition with name, description, and input schema requiring 'filePath'.
export const DOCUMENT_READER_TOOL: Tool = { name: "document_reader", description: "Read content from non-image document-files at specified paths, supporting various file formats: .pdf, .docx, .txt, .html, .csv", inputSchema: { type: "object", properties: { filePath: { type: "string", description: "Path to the file to be read", }, }, required: ["filePath"], }, }; - src/tools/_index.ts:9-9 (registration)Exports array of all tools including DOCUMENT_READER_TOOL for server registration.
export const tools = [DOCUMENT_READER_TOOL, PDF_MERGE_TOOL, PDF_SPLIT_TOOL, DOCX_TO_PDF_TOOL, DOCX_TO_HTML_TOOL, HTML_CLEAN_TOOL, HTML_TO_TEXT_TOOL, HTML_TO_MARKDOWN_TOOL, HTML_EXTRACT_RESOURCES_TOOL, HTML_FORMAT_TOOL, TEXT_DIFF_TOOL, TEXT_SPLIT_TOOL, TEXT_FORMAT_TOOL, TEXT_ENCODING_CONVERT_TOOL, EXCEL_READ_TOOL, FORMAT_CONVERTER_TOOL]; - src/tools/documentReader.ts:29-36 (helper)Type guard/validator for document_reader input arguments.
export function isFileReaderArgs(args: unknown): args is FileReaderArgs { return ( typeof args === "object" && args !== null && "filePath" in args && typeof (args as FileReaderArgs).filePath === "string" ); }