Snowflake
This Snowflake MCP server by Patrick Freyer provides direct integration with Snowflake data warehouses, enabling AI assistants to execute SELECT queries, explore database schemas, and retrieve table metadata through the Snowflake SDK. Built with TypeScript and featuring comprehensive authentication support through environment variables or MCP configuration, it offers five core tools including read-only query execution with SQL injection protection, database/schema/table listing, and detailed table schema inspection. The implementation includes robust error handling, connection management with automatic reconnection, and flexible configuration options supporting warehouse, database, schema, and role specifications, making it valuable for data analysts and business users who need AI-assisted data exploration, report generation, and schema discovery within their Snowflake environments.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Snowflake from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.