azure_sql_execute_query
AI agents invoke azure_sql_execute_query to trigger actions in Azure SQL MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
A tool that executes arbitrary SQL queries is classified as Execute because it runs code whose effects depend entirely on the query arguments provided by the AI agent. While the description is empty (lowering confidence slightly), the tool name combined with server context makes the function clear.
From the tool's definition Tool named 'azure_sql_execute_query' with empty description, in context of a server that 'enables natural language interactions for data querying' and 'executing SQL queries'.
Attacks that exploit this kind of access
azure_sql_execute_query. It is categorised as a Execute tool in the Azure SQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Azure SQL MCP Server MCP server in PolicyLayer and add a rule for azure_sql_execute_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Azure SQL MCP Server. Nothing to install.
azure_sql_execute_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the azure_sql_execute_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for azure_sql_execute_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
azure_sql_execute_query is provided by the Azure SQL MCP Server MCP server (lostspace003/copilot-studio-azure-sql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →