{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_zaphha672e9f","handle":"iflow-mcp-labeveryday-mcp-pdf-reader","url":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader","links":{"self":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader/record.json","html":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader","markdown":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-labeveryday-mcp-pdf-reader","status":"https://wellknown.network/api/v1/agents/iflow-mcp-labeveryday-mcp-pdf-reader/status","claim":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-labeveryday-mcp-pdf-reader/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-labeveryday-mcp-pdf-reader/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-labeveryday-mcp-pdf-reader/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-labeveryday-mcp-pdf-reader","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_labeveryday_mcp_pdf_reader","summary":"MCP server for reading PDFs with text extraction, image extraction, and OCR","description":"# MCP PDF Reader Server (Python + FastMCP)\n\nA powerful Model Context Protocol (MCP) server built with FastMCP that provides comprehensive PDF processing capabilities including text extraction, image extraction, and OCR for reading text within images.\n\n## Features\n\n- **Text Extraction**: Extract text content from PDF pages\n- **Image Extraction**: Extract all images from PDF files\n- **OCR Capabilities**: Read text from images using Tesseract OCR\n- **Comprehensive Analysis**: Get detailed PDF structure and metadata\n- **Page Range Support**: Process specific page ranges\n- **Multiple Languages**: OCR support for multiple languages\n\n## Prerequisites\n\n### System Dependencies\n\n#### Tesseract OCR\nYou need to install Tesseract OCR on your system:\n\n**Ubuntu/Debian:**\n```bash\nsudo apt update\nsudo apt install tesseract-ocr tesseract-ocr-eng\n```\n\n**macOS:**\n```bash\nbrew install tesseract\n```\n\n**Windows:**\n1. Download from: https://github.com/UB-Mannheim/tesseract/wiki\n2. Install and add to PATH\n3. Or use: `conda install -c conda-forge tesseract`\n\n#### Additional Language Packs (Optional)\n```bash\n# For multiple languages\nsudo apt install tesseract-ocr-fra tesseract-ocr-deu tesseract-ocr-spa\n```\n\n## Installation\n\n### Quick Start with UV\n\n1. **Install UV (if not already installed):**\n```bash\n# macOS/Linux\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n# Windows\npowershell -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n```\n\n2. **Clone/Create the project:**\n```bash\nmkdir mcp-pdf-reader-server\ncd mcp-pdf-reader-server\n```\n\n3. **Initialize and install with UV:**\n```bash\n# Copy the files (pdf_reader_server.py and pyproject.toml)\n# Then install dependencies\nuv sync\n```\n\n4. **Verify installation:**\n```bash\nuv run python -c \"import pytesseract; print(pytesseract.get_tesseract_version())\"\n```\n\n### Alternative: Manual Setup\n\nIf you prefer traditional setup:\n\n1. **Create virtual environment:**\n```bash\npython -m venv .venv\nsource .venv/bin/activate  # On Windows: .venv\\Scripts\\activate\n```\n…","publisher":null,"homepage":"https://github.com/labeveryday/mcp_pdf_reader","repository":"https://github.com/labeveryday/mcp_pdf_reader","version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["fastmcp","mcp","ocr","pdf","text-extraction"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_labeveryday_mcp_pdf_reader","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.ocr","name":"OCR","confidence":1,"provenance":"declared"},{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"}],"categories":["documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_labeveryday_mcp_pdf_reader","registry":"pypi","observedAt":"2026-10-28T05:23:58.735Z","publishedAt":"2026-01-27T07:38:55.790325Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_labeveryday_mcp_pdf_reader","url":"https://pypi.org/project/iflow-mcp_labeveryday_mcp_pdf_reader/","firstSeenAt":"2026-09-09T19:24:45.144Z","fetchedAt":"2026-10-28T05:22:07.631Z","normalizedAt":"2026-10-28T05:22:07.631Z"}]},"firstSeenAt":"2026-09-09T19:24:45.144Z","updatedAt":"2026-10-28T05:23:58.735Z"}