Snowflake documents a Snowflake-hosted Model Context Protocol (MCP) endpoint that fronts governed Snowflake data and Cortex workloads without provisioning a separate MCP bridge VM. Administrators declare tools with SQL (`CREATE MCP SERVER`)—for example Cortex Search queries, Cortex Analyst chat-style messages, Cortex Agent executions, parameterized SQL runners, or custom tools backed by Snowflake-native functions—and clients authenticate using Snowflake OAuth against the MCP revision pinned in Snowflake release notes.
Use cases
- Let conversational assistants query approved Cortex Search services with RBAC-aligned tool manifests
- Expose Cortex Analyst as an MCP tool for finance or operations analysts who already trust Snowflake row access policies
- Offer tightly scoped SYSTEM_EXECUTE_SQL tools for parameterized reporting instead of unmanaged raw SQL uploads
- Chain Cortex Agents as callable MCP tools alongside stored procedures surfaced through GENERIC tool slots
- Centralize audit logging for MCP invocations alongside existing Snowflake query history workflows
Key features
- Cursor
- Claude Desktop
- VS Code MCP extensions
- Custom OAuth-capable MCP clients
Frequently Asked Questions
- Which MCP specification revision does Snowflake advertise?
- Release notes cite compatibility with MCP revision dated 2025-11-25; verify Snowflake quarterly release announcements for bumps.
- How are tools enumerated to clients?
- Snowflake expects operators to populate the `tools` array inside the MCP server YAML, including Cortex Search, Cortex Analyst, SQL execution, Cortex Agent, or custom GENERIC wrappers—each declares metadata Snowflake validates at creation time.
- What security guidance accompanies deployment?
- Documentation stresses OAuth-backed sessions, verifying third-party MCP servers separately, hyphenated host naming to avoid TLS mismatches, and least-privilege roles for discovery versus invocation privileges.
Related
Related
3 Indexed items
DuckDB MCP community extension (`duckdb_mcp`)
The DuckDB-distributed community extension `duckdb_mcp` embeds MCP client and server capabilities directly inside DuckDB. Installers load it via `INSTALL duckdb_mcp FROM community` followed by `LOAD duckdb_mcp`, after which SQL can attach remote MCP servers (stdio/TCP/WebSocket transports), enumerate resources (`mcp_list_resources`), invoke remote tools (`mcp_call_tool`), and wrap responses with `read_csv`/`read_json`/`read_parquet` URIs routed through `mcp://`. In reverse direction, DuckDB can publish tables, queries, and execution-bound tools (`mcp_publish_table`, `mcp_publish_query`, `mcp_publish_execution_tool`) while `mcp_server_start` exposes them to external MCP-compatible clients.
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.
Postgres MCP
pg-mcp-server is a Model Context Protocol server implementation that connects AI agents to PostgreSQL databases. It registers database schemas as MCP resource templates and exposes SQL execution as an MCP tool. Agents can introspect table structures, run parameterized queries, and manage transactions without leaving the chat interface. Designed as a reference implementation for database MCP integrations.