MCP (Model Context Protocol) server for reading and analyzing various file formats including PDF, Excel, Word, and PowerPoint
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-file-contents-reader","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MCP File Contents Reader A Model Context Protocol (MCP) server for reading and analyzing various file formats including PDF, Excel, Word, and PowerPoint documents. ## Features - **Multi-format Support**: Read PDF, Excel (.xlsx, .xls), Word (.docx, .doc), and PowerPoint (.pptx, .ppt) files - **Content Analysis**: Extract and analyze file contents with structured information extraction - **Document Search**: Search for specific content across multiple documents - **File Upload**: Support for temporary file upload and processing - **MCP Integration**: Full Model Context Protocol compliance ## Installation ### Using uvx (Recommended) ```bash uvx mcp-file-contents-reader ``` ### Using pip ```bash pip install mcp-file-contents-reader ``` ### From Source ```bash git clone https://github.com/yourusername/mcp-file-contents-reader.git cd mcp-file-contents-reader pip install -e . ``` ## Usage ### MCP Configuration Add the following to your `mcp.json` configuration file: ```json { "mcpServers": { "file-reader": { "command": "uvx", "args": ["mcp-file-contents-reader"] } } } ``` Or if installed via pip: ```json { "mcpServers": { "file-reader": { "command": "mcp-file-contents-reader" } } } ``` ### Available Tools #### 1. `read_file` Read Excel, PDF, PPT, Word files and return content as text. **Parameters:** - `file_path` (required): Path to the file to read - `sheet_name` (optional): Sheet name for Excel files - `page_range` (optional): Page range for PDF files (e.g., '1-5' or '1,3,5') #### 2. `search_documents` Search for specific content in Documents directory and analyze files. **Parameters:** - `keywords` (required): Keywords to search for in file content - `search_path` (optional): Directory path to search (default: ~/Documents) - `file_types` (optional): File types to search (default: ["pdf", "docx", "xlsx", "pptx", "doc", "xls", "ppt"]) #### 3. `analyze_file_content` Analyze specific file content in de…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.