Pdf Mcp
by jztancommunityv1.13.1
35
5
This MCP server enables AI agents to read, search, and extract content from PDF files using specialized tools and SQLite-based caching for persistence across server restarts.
From the registry: Production-ready MCP server for PDF processing with intelligent caching.
Install & configure
Prerequisites
- requiredPython 3.10+Python runtime required
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `pdf-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.10+** — Python runtime required
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["pdf-mcp"]
- optional environment variables:
- `PDF_MCP_CACHE_DIR`: Cache directory (default: ~/.cache/pdf-mcp) (example: `/path/to/cache`)
- `PDF_MCP_CACHE_TTL`: Cache TTL in hours (default: 24) (example: `24`)
Note: 8 tools for reading, searching, and extracting PDF content. Uses SQLite caching. Semantic search requires pip install 'pdf-mcp[semantic]' and downloads ~67MB ONNX model on first use.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: 8 tools for reading, searching, and extracting PDF content. Uses SQLite caching. Semantic search requires pip install 'pdf-mcp[semantic]' and downloads ~67MB ONNX model on first use.
Tools (8)
pdf_info
Get document information including page count, metadata, and estimated token count.
pdf_read_pages
Read specific pages to manage context size.
pdf_read_all
Read an entire document in one call.
pdf_search
Search for relevant pages within the PDF.
pdf_semantic_search
Find pages by conceptual similarity rather than exact keywords.
pdf_get_toc
Retrieve the table of contents of the PDF.
pdf_cache_stats
View cache statistics.
pdf_cache_clear
Clear expired PDF cache entries.
Environment variables
PDF_MCP_CACHE_DIRrequiredCache directory for storing cached PDF data.PDF_MCP_CACHE_TTLrequiredCache TTL in hours.Prerequisites
- • Python 3.10+
Packages
pdf-mcp
pypiv1.13.1transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- May 21, 2026
- Last commit
- May 12, 2026
- Registry name
- io.github.jztan/pdf-mcp