mcp-docs-reader
@AIMIZING
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.
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.
Frequently asked questions
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.
Basic information
More Memory & Knowledge MCP servers
Context Portal MCP (ConPort)
GreatScottyMacContext Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.
Docs MCP Server
araboldGrounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
ctxfile
ctxfileLocal-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
MCP server for Obsidian
MarkusPfundsteinMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Agimem
Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
Comments