PDF Reader
MCP PDF Reader provides a server for extracting and processing content from PDF documents. Built using FastMCP and PyMuPDF (fitz), it offers three main tools: reading normal text from PDFs page by page, extracting text using OCR with language and resolution options, and retrieving images from specific pages in base64 format. The server maintains a directory for PDF resources and implements caching to improve performance. It's particularly valuable for AI assistants that need to analyze, search, or extract information from PDF documents without handling the complexities of PDF parsing directly.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-30.
Scan details: Circle-IR · 2026-09-30 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/deepseekmine/mcp-pdf-reader
- Author type
- human
- Last scanned
- 2026-09-30
- Updated
- 2026-09-30
Use via MCP
Resolve PDF Reader from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.