A PDF Reader MCP server that enables AI agents to securely extract text, metadata, and page information from PDF files within a project directory. Built by shtse8, it uses pdfjs-dist to process both local files and remote URLs, supporting multi-source requests with per-source page selection. The server enforces strict path resolution to prevent access outside the project root, making it ideal for scenarios where agents need to analyze PDF documents without requiring full file content to be sent to the model.
Cognium trust score
50%
Tier
Scanned
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 2026-09-19.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.