Top query digests from
AI agents call slow_queries to retrieve information from Querybridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical or analytical data about query performance rather than executing, modifying, or deleting data. Even though it accesses database metadata, it poses minimal risk as a read-only diagnostic tool. The incomplete description slightly reduces confidence, but the name strongly indicates a passive analysis function rather than an operational query.
From the tool's definition Tool name 'slow_queries' and context indicate retrieval of query performance metrics/digests from the database.
Attacks that exploit this kind of access
Top query digests from. It is categorised as a Read tool in the Querybridge MCP Server, which means it retrieves data without modifying state.
Register the Querybridge MCP server in PolicyLayer and add a rule for slow_queries: 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 Querybridge. Nothing to install.
slow_queries 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 slow_queries 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 slow_queries. 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.
slow_queries is provided by the Querybridge MCP server (mahmoudhassanmustafa/querybridge-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 →