Read-only SELECT query for custom analysis. Results capped at 50 rows.
AI agents call run_sql 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.
The tool explicitly states it is read-only and only allows SELECT queries, meaning no data modification or deletion is possible. However, it allows arbitrary SQL SELECT statements against a local SQLite database containing telemetry and governance data, which could expose sensitive organizational information if misused.
From the tool's definition 'Read-only SELECT query for custom analysis. Results capped at 50 rows.'
Attacks that exploit this kind of access
Read-only SELECT query for custom analysis. Results capped at 50 rows. 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 run_sql: 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.
run_sql 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 run_sql 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 run_sql. 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.
run_sql 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 →