AI agents call impact_of to retrieve information from Graphdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes dependency information from an indexed Rails codebase graph. It answers 'what code depends on this?' — a pure read operation. While the information could inform risky refactorings, the tool itself only queries and reports existing relationships. No code is modified, executed, deleted, or deployed.
From the tool's definition Tool performs static analysis via 'predict what may break if name changes' — it queries the graph to compute transitive caller relationships without modifying code, executing commands, or triggering side effects.
Attacks that exploit this kind of access
Transitive callers — predict what may break if name changes. It is categorised as a Read tool in the Graphdb MCP Server, which means it retrieves data without modifying state.
Register the Graphdb MCP server in PolicyLayer and add a rule for impact_of: 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 Graphdb. Nothing to install.
impact_of 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 impact_of 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 impact_of. 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.
impact_of is provided by the Graphdb MCP server (samagra001/claude-code-graphdb). 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 →