MCP.so
Sign In

mcp-docs-reader

@AIMIZING

Repository

About mcp-docs-reader

A lightweight MCP server that loads PDF files, extracts and chunks their text, builds a semantic vector index, and returns relevant passages to Claude or other AI agents for document-based question answering.

Basic information

Category

Memory & Knowledge

Runtime

python

Transports

stdio

Publisher

AIMIZING

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp_docs_reader": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-docs-reader?

mcp-docs-reader is a lightweight MCP server that loads PDF files from a local folder, extracts and chunks their content, builds a semantic search index, and sends relevant passages to Claude Desktop for document-based question answering. It is intended for use with Claude’s MCP desktop feature.

How to use mcp-docs-reader?

Download or clone the project, set up the uv virtual environment (manually or via setup.bat), and install dependencies. Then edit your Claude Desktop claude_desktop_config.json to include the content from docReader_config.json, replacing the placeholder path with the actual project path. Launch Claude Desktop; it will automatically connect to the MCP tool.

Key features of mcp-docs-reader

  • Loads and processes PDF documents from a local docs/ folder
  • Extracts text and splits it into semantic chunks
  • Generates vector embeddings using SentenceTransformer
  • Builds a FAISS-based vector index for semantic search
  • Retrieves top-k relevant chunks based on user query
  • Constructs a prompt with passages and returns it to Claude

Use cases of mcp-docs-reader

  • Ask Claude questions based on your local PDF documents.
  • Summarize key points from registered file contents.

FAQ from mcp-docs-reader

What is mcp-docs-reader intended for?

It is intended for use with Claude Desktop’s MCP feature to enable document-based question answering from local PDF files.

What kind of documents does it support?

It supports PDF files located in a local docs/ folder.

How are documents processed?

Text is extracted, split into semantic chunks, embedded with SentenceTransformer, and indexed with FAISS for semantic search.

What does mcp-docs-reader return to Claude?

It constructs and returns a prompt containing top-k relevant passages along with the user’s question.

Comments

More Memory & Knowledge MCP servers

Notion MCP Integration

danhilse

A simple MCP integration that allows Claude to read and manage a personal Notion todo list

208

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

Docs MCP Server

arabold

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

1.5K

Mcp Knowledge Graph

shaneholloman

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

871

Obsidian MCP Server

cyanheads

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

618