The zilliztech/mcp-server-milvus project (documented at milvus.io/docs/milvus_and_mcp.md) exposes Milvus vector-database operations to MCP clients such as Claude Desktop and Cursor. The recommended launch path is `uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530` without a separate install step, with optional `MILVUS_URI`, `MILVUS_TOKEN`, and `MILVUS_DB` environment variables. Tools listed in Milvus docs include `milvus-text-search`, `milvus-hybrid-search`, `milvus-multi-vector-search`, `milvus-query`, and `milvus-count` for collection management, semantic retrieval, filtered hybrid search, and entity counts.
Use cases
- Let coding agents run hybrid vector+metadata searches against Milvus collections
- Debug RAG pipelines by querying and counting entities without hand-written SDK scripts
- Prototype multi-vector retrieval flows from Cursor using documented MCP tools
- Connect local Milvus standalone or Zilliz Cloud URIs via MILVUS_URI configuration
- Manage collections through MCP instead of ad-hoc Python notebooks
Key features
- Claude Desktop
- Cursor
Frequently Asked Questions
- Do I need a running Milvus instance?
- Yes. Docs configure `--milvus-uri` or `MILVUS_URI` against local standalone, Docker, or Zilliz Cloud endpoints.
- Is uv required?
- The README recommends running directly with uv—the same pattern shown for Claude Desktop and Cursor samples.
- How does this differ from Pinecone MCP?
- This server targets Milvus/Zilliz stacks and documents Milvus-specific hybrid and multi-vector tools rather than Pinecone indexes.
Related
Related
3 Indexed items
ClickHouse MCP Server
The open-source ClickHouse MCP server (PyPI package `mcp-clickhouse`, repository ClickHouse/mcp-clickhouse) exposes MCP tools such as `run_query`, `list_databases`, and paginated `list_tables` against ClickHouse clusters, defaulting to read-only SQL unless `CLICKHOUSE_ALLOW_WRITE_ACCESS` is enabled. Optional chDB extras add `run_chdb_select_query` for embedded queries over files and URLs. HTTP/SSE transports require authentication via `CLICKHOUSE_MCP_AUTH_TOKEN`, FastMCP OAuth/OIDC providers, or explicit `CLICKHOUSE_MCP_AUTH_DISABLED=true` for local dev; a `/health` endpoint supports orchestrator probes without credentials per README guidance.
Neon MCP Server
Official Neon MCP integration exposes Neon Postgres projects to MCP-capable assistants via Streamable HTTP (`https://mcp.neon.tech/mcp`), legacy SSE (`https://mcp.neon.tech/sse`), or a locally launched `@neondatabase/mcp-server-neon` package. Documentation lists tools for project and branch lifecycle, SQL execution, migration rehearsal branches, slow-query diagnostics, Neon Auth provisioning, Data API setup, and embedded Neon docs retrieval—each mapped to Neon API operations.
Qdrant MCP Server
Official Qdrant MCP server implementation that gives AI agents a semantic memory layer backed by Qdrant vector search. It exposes MCP tools for storing information and retrieving relevant context, so assistants can persist and recall facts across sessions instead of relying only on short chat history.