integrations tools azure-sql

    Azure SQL MCP for your AI agent

    Cogny's Azure SQL integration exposes 4 tools (4 read) to an AI agent over MCP. The same tools are available on every plan, from your own AI client or inside the Cogny app.

    • 4readonly reads data.
    • 0writecreates or changes something.
    • 0destructivedeletes, removes or replaces something.

    Over MCP your own AI client asks before it runs a write. To take a tool away from your agent, block it in Settings → Integrations. Plans, approvals and limits

    set it up.

    Add Cogny to your AI client once, then connect Azure SQL in Cogny. Every Azure SQL tool below appears in the client.

    • Claude CodeRun claude mcp add --transport http cogny https://app.cogny.com/mcp, then authorise in the browser.
    • Claude.aiSettings → Connectors → Add custom connector, URL https://app.cogny.com/mcp, then log in and pick your workspace.
    • ChatGPTSettings → Apps → Advanced settings → Developer mode → Create app, URL https://app.cogny.com/mcp, authentication OAuth.
    • CursorIn Cogny, Settings → Data & Integrations → Connect AI Clients shows the block to paste into .mcp.json, with an API key.
    • CodexRun codex mcp add cogny --url https://app.cogny.com/mcp.

    Full setup, and how to undo it

    what each tool does.

    Read 4 · only reads data

    • get_server_infoReadConnection check: database name, login and user, SQL edition / service objective, and the user's role membership and write permissions.
    • list_tablesReadList user tables and views with approximate row counts.
    • describe_tableReadColumns (type, nullability, primary key), foreign keys, and a few sample rows for one table or view.
    • run_queryReadRun one read-only T-SQL query and return the rows.

    Exact input schemas come from tools/list once Azure SQL is connected; the free plan is enough to check. Missing something? Your agent can ask for it with request_feature.