Trace how named symbols relate in the dependency graph → returns subgraph + Mermaid diagram. Input is NATURAL LANGUAGE only — NOT SQL. Must contain symbol/class names (e.g.
AI agents call graph_query to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
graph_query is a read-only navigation tool that traces symbol relationships in a dependency graph and returns visualization data. It has no mutation capabilities, does not execute code, and cannot modify the underlying graph structure. The natural language input constraint further limits it to safe introspection.
From the tool's definition Tool description states it 'returns subgraph + Mermaid diagram' and 'Input is NATURAL LANGUAGE only — NOT SQL', indicating a query-only operation that retrieves and visualizes dependency information without modification.
Documented attack patterns abuse exactly the kind of access graph_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for graph_query:
{
"version": "1",
"default": "deny",
"tools": {
"graph_query": {}
}
}graph_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Trace how named symbols relate in the dependency graph → returns subgraph + Mermaid diagram. Input is NATURAL LANGUAGE only — NOT SQL. Must contain symbol/class names (e.g. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for graph_query: 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 Trace. Nothing to install.
graph_query 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 graph_query 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 graph_query. 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.
graph_query is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.