DocMCP

PDF vector search engine using ChromaDB with web UI for document ingestion, semantic search, and collection management.

GitHub
Category MCP Servers
Added Mar 28, 2026
Views 89

About

Local PDF ingestion and semantic search server backed by ChromaDB vector database. Supports multiple ONNX embedding models for fully offline operation. Includes a web interface for document ingestion, search with relevance scoring, and collection management. Provides tools for searching across ingested PDFs, listing sources, retrieving full documents, and managing collections.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/docmcp.svg)](https://hifriendbot.com/ai-list/docmcp/)
Listed on AiList

Compare

DocMCP vs ChromaDB DocMCP vs RAG DocMCP vs ArXiv Intelligence

Similar Projects

ChromaDB

41

Integrates ChromaDB vector database capabilities for efficient semantic document search, storage, and retrieval in natural language processing and information retrieval applications.

Web Apps

RAG

5

Provides cloud-based document management and semantic search using OpenAI embeddings with in-memory vector storage, enabling retrieval-augmented generation workflows through document ingestion, metadata filtering, and cosine similarity search.

MCP Servers

ArXiv Intelligence

1

Research assistant combining ArXiv search, PDF ingestion via DocLing, and semantic memory with ChromaDB.

CLI Tools Python

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project