Breadth-first navigation of FK relationships from a seed row.
AI agents call traverse_fk 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 navigates foreign key relationships to discover related data, similar to a graph traversal or join query. It retrieves and explores existing relationships without creating, modifying, or deleting any data. The breadth-first search pattern is a read-only operation. No side effects are indicated in the description.
From the tool's definition Tool performs 'breadth-first navigation of FK relationships from a seed row' - a traversal/query operation with no modification capabilities. The description indicates data retrieval only.
Attacks that exploit this kind of access
Breadth-first navigation of FK relationships from a seed row. 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 traverse_fk: 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.
traverse_fk 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 traverse_fk 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 traverse_fk. 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.
traverse_fk 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 →