mcp-ollama-qdrant

An MCP server that gives your AI agent a persistent vector memory backed by:

• Ollama for embeddings (tested with qwen3-embedding:8b)

• Qdrant as the vector store

It exposes five tools over the stdio MCP transport:

Payload filtering

search_memory accepts an optional filter JSON string built from payload fields. List values become a MatchAny condition (matches if the payload field contains any of the values), scalar values become exact matches. Multiple conditions are AND-ed together:

{"tags": ["x"]}                      // payload.tags contains "x"
{"source": "doc1"}                   // exact match
{"tags": ["a", "b"], "source": "s"}  // AND of MatchAny + match

On startup the server connects to Ollama and Qdrant and creates the collection automatically if it does not exist (cosine distance, dimension probed from the embedding model). If the collection already exists with a different vector dimension than the current EMBED_MODEL produces, the server fails fast with a clear error instead of silently storing corrupt vectors — fix it by deleting and recreating the collection, or by switching back to the original embedding model.

Requirements

• Python 3.11+ and uv

• A reachable Ollama instance (default http://192.168.X.X:11434)

• A reachable Qdrant instance (default http://192.168.X.X:6333)

Related MCP server: Qdrant MCP Server

Configuration

Settings resolve in order: CLI flags > environment variables > defaults.

Running

With uv (recommended — handles the venv and sync automatically):

uv sync
uv run mcp-ollama-qdrant            # or: uv run python mcp_server.py
# with overrides:
uv run mcp-ollama-qdrant --qdrant-url http://localhost:6333

Interactive testing / inspection:

uv run mcp dev mcp_server.py

MCP client config

Add to your client's MCP config (Claude Desktop, Hermes, etc.):

{
  "mcpServers": {
    "vector-memory": {
      "command": "uv",
      "args": [
        "--directory", "/path/to/mcp-ollama-qdrant",
        "run", "mcp-ollama-qdrant"
      ],
      "env": {
        "OLLAMA_URL": "http://192.168.X.X:11434",
        "QDRANT_URL": "http://192.168.X.X:6333",
        "EMBED_MODEL": "qwen3-embedding:8b",
        "COLLECTION_NAME": "agent_scenarios"
      }
    }
  }
}

(Env entries are optional if the defaults already point at your instances.)

For Hermes ~/.hermes/config.yaml:

mcp:
  servers:
    vector-memory:
      command: uv
      args: ["--directory", "/path/to/mcp-ollama-qdrant", "run", "mcp-ollama-qdrant"]

Testing

End-to-end smoke test against live Ollama + Qdrant (saves a few memories, searches for them, prints similarity scores):

uv sync
uv run python test_server.py

Notes

• All diagnostics are logged to stderr; stdout is reserved for the stdio MCP transport.

• Dependency pins: numpy<2, qdrant-client<1.15, mcp[cli]<2 — chosen for compatibility with older x86-64 hardware (pre-x86-64-v2) and the mcp v2 FastMCP rename. Adjust only with reason.