Inspect a file, class, or directory hierarchy to identify contained classes and methods without reading source code. Use the returned JSON structure to decide which files to read.
MIT
602,772 tools. Updated 2026-09-23 14:09
"Methods for Reading PDF Files" matching MCP tools:
- Convert PDF files to markdown format for easier editing and content extraction. Use server file paths or online URLs to transform PDF content into readable text.MIT
- Retrieve class definitions and specific methods without reading entire files to reduce token usage by 80%+ in code navigation.MIT
- Locate PDF files in directories using glob patterns to filter by filename, returning file details for processing with PDF reading tools.MIT
- Extract file signatures including headers, types, and method prototypes to understand code structure without reading entire files.MIT
- Extract text content from binary files (DOCX, XLSX, PPTX, PDF) in the workspace. Faster alternative to reading via filesystem.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceMemory-efficient MCP server for reading and splitting large PDF files page by page using PyMuPDF.3MIT
- FlicenseCqualityDmaintenanceAn MCP server that provides a tool to extract text content from local PDF files, supporting both standard PDF reading and OCR capabilities with optional page selection.133-
Matching MCP Connectors
- PDF ToolkitOAuth
Convert PDFs/images to Word, Excel, and Markdown. Split, merge, and watermark PDF files.
PDF Toolkit converts PDFs/images to Word, Excel, and Markdown, splits and merges PDFs, creates PDFs from images, adds text watermarks, and provides asynchronous task lookup. It supports OAuth and manual API Key authorization.
- Merge multiple PDF files into one combined document. Files are processed in the order provided, and the merged PDF is returned as a base64-encoded string.MIT
- Fetch any URL with no domain restrictions and return page content as clean markdown. Handles HTML, JSON, XML, CSV, and PDF files.MIT
- Extract and convert PDF, Word, Excel, and PowerPoint files to Markdown format using the NiuTrans API for readable text content.MIT
- Get a structural outline of source files: list classes, functions, methods, fields, and structs with their line ranges, enabling navigation without reading the entire file.MIT
- Retrieve reading annotations and notes for a Zotero item by its key, including PDF highlights, margin comments, and standalone notes. Ideal for literature review and analyzing reading insights.MIT
- List PDF figures with diagnostic information, optionally filtered by outline node. Prepare for focused figure reading.MIT
- Retrieve document metadata including title, author, dates, page count, and file size without reading the content. For PDF files, additionally returns subject, creator, producer, and version.MITDestructive
- Combine multiple PDF files into one document. Supports file paths, URLs, or base64 encoded PDF contents.MIT
- Retrieves the document outline from EPUB or PDF files, enabling outline-first navigation, chapter selection, and node-scoped reading.MIT
- Merge multiple PDF files into one document by providing base64 encoded PDF data or file paths in order.MIT
- Merge multiple PDF files into a single PDF by providing input file paths and an output destination.MIT
- Extract specific pages from a PDF into separate PDF files. Specify file path, page numbers, and output directory.MIT
- Extract metadata from PDF files to access document information without reading entire content. Use this tool to retrieve details like title, author, and creation date from PDF documents.Apache 2.0
- Combine multiple PDF files into one document using the merge-pdfs tool from the mcp-pdf-tools server. Specify input files and output path to create a single PDF.-
- Search for PDF files in directories using pattern matching to locate specific documents quickly.-