PDF MCP
PDF MCP is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Agentic RAG over your PDFs, with page-level evidence to check every answer. It has 171 GitHub stars, is released under the MIT license and runs locally with uvx pdf-mcp.
github.com/jztan/pdf-mcp (opens in a new tab)
Data as of from the GitHub API and the official MCP registry; description from the project's repository. Report an error
Install PDF MCP
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"pdf-mcp": {
"command": "uvx",
"args": [
"pdf-mcp"
],
"env": {
"PDF_MCP_CACHE_DIR": "your-value",
"PDF_MCP_CACHE_TTL": "your-value",
"PDF_MCP_CACHE_MAX_MB": "your-value"
}
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --env PDF_MCP_CACHE_DIR=your-value --env PDF_MCP_CACHE_TTL=your-value --env PDF_MCP_CACHE_MAX_MB=your-value --transport stdio pdf-mcp -- uvx pdf-mcpCursor
{
"mcpServers": {
"pdf-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"pdf-mcp"
],
"env": {
"PDF_MCP_CACHE_DIR": "your-value",
"PDF_MCP_CACHE_TTL": "your-value",
"PDF_MCP_CACHE_MAX_MB": "your-value"
}
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"pdf-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"pdf-mcp"
],
"env": {
"PDF_MCP_CACHE_DIR": "your-value",
"PDF_MCP_CACHE_TTL": "your-value",
"PDF_MCP_CACHE_MAX_MB": "your-value"
}
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
Environment variables
Variables the server reads at startup.
| Name | Required | Description |
|---|---|---|
PDF_MCP_CACHE_DIR | No | Directory for storing PDF cache (default: ~/.cache/pdf-mcp) |
PDF_MCP_CACHE_TTL | No | Optional time expiry in hours; unset keeps a document while its PDF exists |
PDF_MCP_CACHE_MAX_MB | No | Cache size cap in MB, least recently used evicted first (default: 2048; 0 = no cap) |
Tools (13)
Parsed from the Tools section of the README; check the repository for the current list.
pdf_infoPage count, metadata, TOC summary, scanned-page detection. Call first.
pdf_searchHybrid search (keyword + semantic) by page or section; hits carry an excerpt, source coordinates, the enclosing…
pdf_read_pagesRead specific pages or ranges, with OCR on demand, tables, and embedded images
pdf_read_allRead a whole document in one call, byte-capped
pdf_get_tocFull table of contents for documents with many bookmarks
pdf_render_pagesRender pages as PNG for vision models: diagrams, handwriting, scans
pdf_extract_chartChart data as exact (x, y) tables, read from plot geometry
pdf_corpus_warmWarm a folder of PDFs into the cache within a time budget; OCRs scanned pages between calls (ocr)
pdf_corpus_overviewPer-document triage cards for a folder
pdf_corpus_searchSearch across a folder; hits carry document and page provenance
pdf_cache_statsPer-document cache breakdown and total size
pdf_cache_clearClear expired or all cache entries
server_infoWhich optional features and config are active
About PDF MCP
Agentic RAG over your PDFs, with the evidence to check every answer. The agent decides when to search; pdf-mcp does the retrieval and hands back excerpts, each with the page it came from. When the extracted text might be wrong, the agent can render that page and check it against what's actually printed. Hidden text, including injected instructions, is flagged, not silently passed on.
- ai
- claude
- document-processing
- llm
- mcp
- python
- codex-cli
- opencode
- mcp-server
Similar MCP servers
More ai & search MCP servers
SerpApi
serpapi/serpapi-mcp
Official SerpApi MCP server for Google, Bing, and other search engines.
Active · last commit Nov 12, 2026
OfficialAI & searchPythonContextLattice
sheawinkler/ContextLattice
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Active · last commit Nov 16, 2026
AI & searchGoMCP Image
shinpr/mcp-image
AI image generation and editing with prompt optimization and quality presets.
Active · last commit Nov 13, 2026
AI & searchTypeScriptmcpsurfr
nkapila6/mcpsurfr
Local web search with multi-engine deep research and on-device re-ranking.
Active · last commit Oct 29, 2026
AI & searchPythonMengram
alibaizhanov/mengram
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows.
Active · last commit Nov 9, 2026
AI & searchPythondocling.rs
docling-project/docling.rs
Documents to Markdown for agents: PDF layout, tables and OCR, Office, HTML, scans.
Active · last commit Nov 16, 2026
AI & searchRust
How do I install the PDF MCP MCP server?
Add the command uvx pdf-mcp to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is PDF MCP free?
The server is open source under the MIT license, so running it is free. It does not declare any required API key.
Is PDF MCP actively maintained?
The most recent commit was on Nov 14, 2026. The latest release is v3.8.0, published Nov 14, 2026. appsgit only lists MCP servers with a commit in the last six months.