Pdf Document MCP
MCP server that extracts, converts, merges and summarizes PDF documents for AI clients
- Pricing
- Open source
- Platforms
- CLI, self-hosted
- Runs
- Locally
- Version
- 1.0.8
- Listing updated
- today
Similar MCP servers
About Pdf Document MCP
Pdf Document MCP is an open-source MCP server for files and documents. It runs locally on your machine and is started by your AI client.
The README describes this as a document processing toolkit for AI assistants. It covers pulling text out of PDFs, converting them to Markdown, merging several files, extracting tables and producing summaries, all exposed as MCP tools over stdio.
The server installs from PyPI as pdf-document-mcp and is launched through uvx or the pdf-document-mcp command, with a Claude Desktop config snippet provided. Smithery is listed as an alternative install route. The README names three example tools: extract_text_from_pdf, convert_pdf_to_markdown and merge_pdfs.
It suits people who want an assistant to read, reformat or combine PDF files locally without uploading them to a separate service. The README also notes that the MIT-licensed source can be self-hosted, and that the publisher, MEOK AI Labs, sells per-job work separately.
Install
Run in a terminal
claude mcp add pdf-document-mcp -- uvx pdf-document-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"pdf-document-mcp": {
"command": "uvx",
"args": [
"pdf-document-mcp"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"pdf-document-mcp": {
"command": "uvx",
"args": [
"pdf-document-mcp"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"pdf-document-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"pdf-document-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"pdf-document-mcp": {
"command": "uvx",
"args": [
"pdf-document-mcp"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"pdf-document-mcp": {
"command": "uvx",
"args": [
"pdf-document-mcp"
]
}
}
}Using several servers? Build one config file with the MCP config generator.
Tools this server provides (3)
Taken from the project documentation; the running server may differ.
- extract_text_from_pdf
- Extracts text from a PDF file.
- convert_pdf_to_markdown
- Converts a PDF file to Markdown.
- merge_pdfs
- Merges multiple PDF files.
What it does
- Text extraction from PDFs
- Pulls plain text out of PDF files through the extract_text_from_pdf tool.
- Markdown conversion
- Converts PDF content into Markdown using convert_pdf_to_markdown.
- Merging multiple files
- Combines several PDF documents into one with the merge_pdfs tool.
- Table extraction
- Lists table extraction among the toolkit's capabilities.
- Document summarization
- Summarizes document content as one of its listed functions.
- Stdio transport setup
- Runs over stdio and installs via pip, uvx or Smithery.
Good for
- Letting an AI assistant read the text of a PDF report
- Converting PDF documents into Markdown for notes or editing
- Merging several PDF files into a single document before sharing
- Pulling tables out of PDFs for analysis
- Getting a quick summary of a long PDF
Pricing
Open source
MIT-licensed and free to self-host; the publisher charges per job for separate services.
Pdf Document MCP FAQ
How do I install it?
The README gives pip install pdf_document_mcp, or the Smithery command npx -y @smithery/cli@latest install pdf-document-mcp --client claude.
What transport does it use?
It uses stdio transport, launched with the pdf-document-mcp command or uvx.
Is it free to self-host?
The README states that the repository's source is MIT-licensed and free to self-host.
Is Pdf Document MCP free?
Yes. Pdf Document MCP is open source, so you can use and self-host it for free.
How do I add Pdf Document MCP to Claude Code?
Run this command in your terminal: claude mcp add pdf-document-mcp -- uvx pdf-document-mcp
What are the best alternatives to Pdf Document MCP?
The closest alternatives to Pdf Document MCP are Pdf Tools Ai MCP, Pdf Merge Ai MCP, Pdf MCP, Markdown Ai MCP and Doc Extract MCP.
Where this comes from
- Description: written from the project's README and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.