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.
Use cases
- Spinning up ephemeral Neon branches before merging risky schema migrations
- Letting coding agents fetch connection strings and run exploratory SQL against dev databases
- Automating Neon project inventory searches across organizations during onboarding
- Reviewing execution plans through Neon-provided explain helpers during query tuning workflows
- Provisioning Neon Auth or Data API resources without switching to the Neon Console UI
Key features
- Cursor
- VS Code
- Claude Code
- Windsurf
- ChatGPT
- Zed
Frequently Asked Questions
- Is OAuth supported?
- Yes. Connecting to `https://mcp.neon.tech/mcp` triggers OAuth in the browser per Neon docs; API-key headers are documented for environments where OAuth is unavailable.
- Can agents delete production projects?
- Tooling includes destructive operations such as `delete_project`; Neon recommends MCP only for development workflows, human review before destructive actions, and avoiding production datasets.
- What if my client lacks Streamable HTTP?
- Neon documents falling back to `https://mcp.neon.tech/sse` for SSE-only MCP clients (API-key flows differ—see Neon troubleshooting notes).
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.
Milvus MCP Server
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.
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.