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
524,517 tools. Updated 2026-09-06 16:13
"Methods for Reading PDF Files" matching MCP tools:
- 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
- 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
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 Redaction MCPOAuth
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Semantic product search over Singapore e-commerce, ranked by an auditable entropy-based value-score
- Extract text content from binary files (DOCX, XLSX, PPTX, PDF) in the workspace. Faster alternative to reading via filesystem.MIT
- 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
- Retrieve document metadata such as file type, size, and modification time without reading the full content. Get page counts for PDFs or line counts for text files to quickly assess document details.MIT
- Extract and convert PDF, Word, Excel, and PowerPoint files to Markdown format using the NiuTrans API for readable text content.MIT
- Extract and list PDF tables with diagnostic information, optionally filtered by outline node, to enable table-centric reading.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
- Search for text patterns in remote files via SSH without downloading full content, using token-efficient methods.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
- 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