Conversations and connector calls for a specific Azure AD user_id.
AI agents call search_by_user to retrieve information from Copilot Insights MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing telemetry and governance data from Microsoft Copilot Studio without creating, modifying, or deleting records. It is a read-only retrieval operation.
From the tool's definition Tool name is 'search_by_user' and description states it retrieves 'Conversations and connector calls for a specific Azure AD user_id' — purely retrieval operations with no modification or deletion.
Attacks that exploit this kind of access
Conversations and connector calls for a specific Azure AD user_id. It is categorised as a Read tool in the Copilot Insights MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Copilot Insights MCP Server MCP server in PolicyLayer and add a rule for search_by_user: 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 Copilot Insights MCP Server. Nothing to install.
search_by_user 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 search_by_user 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 search_by_user. 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.
search_by_user is provided by the Copilot Insights MCP Server MCP server (syokiel/copilot-insights). 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 →