Extract content from documents including Excel, Word, PowerPoint, PDF, and text files using raw or paginated reading modes with interactive UI support.
MIT
127,484 tools. Last updated 2026-05-05 18:53
"MCP servers for reading and parsing PDF, Word, and PowerPoint documents" matching MCP tools:
- Extract figures, tables, and equations from PDF documents using layout detection. Returns base64-encoded images of detected elements with metadata from academic papers or any PDF URL.Apache 2.0
- Monitor and manage connected MCP servers by listing their connection status, available tools, and health metrics for operational oversight.
- Retrieve metadata and statistics about Obsidian notes, including tags, dates, size, frontmatter properties, word count, and link information without reading the content.MIT
- Upload a local document file to a Miro board. Supports PDF, Word, Excel, PowerPoint, text, and CSV files up to 6 MB.
- Extract document metadata including title, author, page count, word count, format, file size, and dates to understand document structure before reading content.MIT
Matching MCP Servers
- Flicense-qualityCmaintenanceEnables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.Last updated1
- Flicense-qualityCmaintenanceAn MCP Server that provides a conversational interface to the UK Open Banking account information API, allowing agents to interact with bank account data through natural language commands.Last updated
Matching MCP Connectors
Send transactional pdfs for AI agents via SMTP. Templates included.
US visa bulletin data and CBP border wait times. 3 MCP tools for immigration and travel planning.
- Retrieve AWS documentation pages and convert them to markdown format for easier reading and integration. Supports chunked reading for long documents.Apache 2.0
- Convert PDF files to Word, Excel, PowerPoint, text, or images. Specify a source URL and target format, optionally selecting page ranges for conversion.
- Extract text or images from PDF files for vision LLMs, handling both text and scanned documents with configurable extraction modes.MIT
- Add text or image watermarks to PDF documents to protect content and establish ownership. Customize watermark position, opacity, and scale for document security.MIT
- Retrieve specific financial documents by ID to access content, metadata, and extracted PDF text for comprehensive market analysis.MIT
- Extract content from Word (.docx) documents and convert it to Markdown format for reading, summarizing, editing, or processing within Claude.GPL 3.0
- Manage quarantined MCP servers and tools to prevent Tool Poisoning Attacks (TPAs). Supports server-level quarantine and tool-level approval for schema changes.
- Analyze text to get detailed statistics including character, word, line, sentence, and paragraph counts with estimated reading time.MIT
- Convert Microsoft Office documents (Word, Excel, PowerPoint) to Markdown format with image extraction and optimization for Claude to read and process.MIT
- Analyze Markdown documents to extract detailed statistics including word count, reading time, and structural elements like headings, tables, and code blocks.MIT
- Extract and convert PDF, Word, Excel, and PowerPoint files to Markdown format using the NiuTrans API for readable text content.MIT
- Convert PDF, Word, Excel, and PowerPoint files to Markdown format using an absolute file path to extract and structure document content.MIT
- Extract figures, tables, and equations from PDF documents using layout detection. Returns base64-encoded images with metadata for academic papers or any PDF URL.Apache 2.0