Walk the dependency graph from a starting symbol or file using BFS/DFS, with a hard token budget on the response. Use when you want a structured
AI agents call traverse_graph 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.
This tool retrieves and queries structural information about code dependencies. It performs graph traversal to analyze relationships but does not create, modify, delete, or execute anything. The token budget constraint further suggests it is a bounded read operation. This falls squarely into the Read category with low risk.
From the tool's definition Tool description states it 'Walk[s] the dependency graph from a starting symbol or file' with BFS/DFS traversal. The verb 'walk' and 'traverse' indicate read-only navigation and querying of existing dependency data.
Documented attack patterns abuse exactly the kind of access traverse_graph 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 traverse_graph:
{
"version": "1",
"default": "deny",
"tools": {
"traverse_graph": {}
}
}traverse_graph 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.
Walk the dependency graph from a starting symbol or file using BFS/DFS, with a hard token budget on the response. Use when you want a structured. 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 traverse_graph: 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.
traverse_graph 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_graph 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_graph. 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_graph 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.