Search a specific index for documents in that index
AI agents call query_index to retrieve information from Azure AI Foundry MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though query_index only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Search a specific index for documents in that index. It is categorised as a Read tool in the Azure AI Foundry MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure AI Foundry MCP Server MCP server in PolicyLayer and add a rule for query_index: 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 AI Foundry MCP Server. Nothing to install.
query_index 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 query_index 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 query_index. 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.
query_index is provided by the Azure AI Foundry MCP Server MCP server (youssef7788/mcp-foundry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.