Skip to main content

VeloDB Cloud MCP Service Overview

The VeloDB Cloud MCP Service connects AI agents to VeloDB Cloud through the Model Context Protocol (MCP). After you add the MCP Server URL to a supported client, you can explore warehouse metadata and run read-only SQL in natural language.

You can use the service from MCP-compatible clients such as Claude Code, Cursor, Visual Studio Code, and Codex, or route it through an MCP gateway such as LiteLLM.

Query workflow​

The agent checks the warehouse connection, discovers databases, tables, and columns, and generates a read-only SQL query to answer your request.

VeloDB MCP Service workflow: check service health, discover metadata, and query the warehouse with read-only SQL

Query capabilities​

Once connected, you ask questions in plain language, and the AI agent calls the matching MCP tool automatically.

Metadata discovery​

What you wantJust sayTool called
See the databases"List all databases"list_databases
See the tables in a database"List the tables in the sales database"list_tables
See a table's structure"Show the columns of the orders table"describe_table

Read-only SQL queries​

The agent discovers the available tables and columns, generates a read-only SQL statement, and calls execute_query. The result depends on how accurately the agent interprets the request and generates the SQL.

What you wantJust sayTool called
Query data"Show the top 10 orders"execute_query
Aggregate data"Count orders by status"execute_query

execute_query accepts read-only SQL only, including SELECT, SHOW, DESCRIBE, and EXPLAIN. DML, DDL, stacked statements, and SELECT INTO OUTFILE/DUMPFILE are blocked.

AI agent query workflow​

The agent follows this workflow for each conversation:

  1. Call get_query_guide to load the query workflow.
  2. Call check_service_health to verify the VeloDB Cloud connection.
  3. Call list_databases, list_tables, and describe_table to discover the data available to the warehouse SQL user.
  4. For data queries, generate a read-only SQL statement and call execute_query.

Security and permissions​

  • Each request uses the warehouse SQL user credentials supplied by the MCP client. Queries run with that warehouse SQL user's privileges.
  • execute_query accepts read-only SQL statements only.

See also​

  • Get Started to connect an AI client and complete your first query.
On This Page