Snowflake Cortex AI
Snowflake Cortex MCP server by BHANUJ that provides AI assistants with natural language access to Snowflake's AI capabilities through three integrated tools: Text2SQL for converting natural language queries into SQL using Cortex Analyst with semantic models, Cortex Search for document retrieval from PDF content stored in Snowflake stages, and direct SQL execution for running generated queries against data warehouses. Built with TypeScript and the MCP SDK, the implementation uses configurable tool definitions with environment variable substitution, supports streaming responses from Cortex agents, and includes sample data setup for TPC-DS retail analytics and vehicle contract documents. Designed for business users who need conversational access to enterprise data warehouses, analysts requiring semantic search across document repositories, and organizations leveraging Snowflake's native AI services for data exploration without writing SQL directly.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · 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
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Snowflake Cortex AI 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.