Knowledge Base MCP Server (Qdrant)
Read-only MCP server with hybrid search combining dense semantic and sparse keyword retrieval via Qdrant, enabling document querying and fetching for ChatGPT Deep Research.
README
Knowledge Base MCP Server (Qdrant)
Read-only MCP server with hybrid search — dense semantic (all-MiniLM-L6-v2) + sparse keyword (BM-25) — fused with Qdrant's built-in RRF.
Stack
| Layer | Tool | Cost |
|---|---|---|
| MCP framework | FastMCP | Free |
| Vector DB | Qdrant Cloud | Free (1 GB) |
| Embeddings | FastEmbed (local, ONNX) | Free |
| Hosting | Render | Free tier |
| ChatGPT | Deep Research connector | Free (Pro plan) |
Setup
1. Install dependencies
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
2. Set up Qdrant Cloud
- Go to https://cloud.qdrant.io → create a free cluster
- Copy the cluster URL and API key from the Access tab
- The collection is created automatically on first ingest
3. Configure .env
cp .env.example .env
# fill in QDRANT_URL, QDRANT_API_KEY, MCP_API_KEY
4. Upload documents
python ingest.py --file report.pdf --dept 1 --pos 2
python ingest.py --file notes.md
python ingest.py --list
python ingest.py --delete <document_id>
Supported formats: pdf, docx, md, txt, rst
5. Test locally
python server.py
# → http://localhost:8000/mcp
6. Deploy to Render
- Push to GitHub (
.envis gitignored) - Render → New Web Service → Connect GitHub repo
- Add env vars:
QDRANT_URL,QDRANT_API_KEY,KEYCLOAK_REALM_URL,KEYCLOAK_CLIENT_ID - Copy your public URL
7. Connect to ChatGPT
- Settings → Connectors → Add → paste Render URL +
/mcp/ - Auth: Bearer token → your
MCP_API_KEY - Use via
+→ Deep Research → select your connector
Tools (all read-only)
| Tool | Description |
|---|---|
search(query, top_k) |
Hybrid search. Returns point IDs. |
fetch(id) |
Get chunk content by point ID. |
list_documents() |
List all documents. |
get_document(id) |
Full text of a document by document_id. |
search + fetch follow the ChatGPT Deep Research contract.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.