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

Related MCP server: mcp-documentacao

Setup

1. Install dependencies

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

2. Set up Qdrant Cloud

1. Go to https://cloud.qdrant.io → create a free cluster

2. Copy the cluster URL and API key from the Access tab

3. 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

1. Push to GitHub (.env is gitignored)

2. Render → New Web Service → Connect GitHub repo

3. Add env vars: QDRANT_URL, QDRANT_API_KEY, KEYCLOAK_REALM_URL, KEYCLOAK_CLIENT_ID

4. 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)

search + fetch follow the ChatGPT Deep Research contract.