azure_sql_search
AI agents call azure_sql_search to retrieve information from Azure SQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the name 'search' and context of a SQL server with query capabilities strongly suggest this retrieves data without side effects. However, confidence is moderate (0.75) because the description is uninformative and we cannot definitively rule out that it might execute arbitrary queries like the 'execute_query' sibling tool.
From the tool's definition Tool name 'azure_sql_search' indicates a search/query operation. The server description mentions 'data querying' as a core capability.
Attacks that exploit this kind of access
azure_sql_search. It is categorised as a Read tool in the Azure SQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure SQL MCP Server MCP server in PolicyLayer and add a rule for azure_sql_search: 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_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the azure_sql_search 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_search. 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_search 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 →