This package has been merged into official repo, please use the official repo instead.
LocalAbout This package has been merged into official repo, please use the official repo instead.
This package has been merged into the official pymupdf4llm-mcp repository. It provides an MCP server for exporting PDFs to Markdown for LLM use; the README directs users to the official repository.
Key features
- 01PDF-to-Markdown export
- 02stdio and SSE modes
Use cases
- 01Convert PDFs for LLM processing
- 02Connect an MCP client to PDF conversion
MCP support
It exposes pymupdf4llm PDF-to-Markdown conversion through an MCP server, runnable in stdio or SSE mode.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEThis package has been merged into official repo, please use the official repo instead.
https://github.com/pymupdf/pymupdf4llm-mcp
pymupdf4llm-mcp
MCP Server for pymupdf4llm, best for export PDF to markdown for LLM.
- Github repository: https://github.com/ai-zerolab/pymupdf4llm-mcp/
- Documentation https://ai-zerolab.github.io/pymupdf4llm-mcp/
Quick Start
Run the following command to run the MCP server:
uvx pymupdf4llm-mcp@latest stdio # stdio mode
# or
uvx pymupdf4llm-mcp@latest sse # sse mode
Configure your cursor/windsurf/... and other MCP client to this server:
{
"mcpServers": {
"pymupdf4llm-mcp": {
"command": "uvx",
"args": [
"pymupdf4llm-mcp@latest",
"stdio"
],
"env": {}
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.