One-shot debugging entry point. Given a bug description or error message, returns ranked candidate symbols enriched with callers, callees, and impact risk. Replaces the semantic_search → get_context → impact_analysis chain with a single call to save tokens.
AI agents call debug_trace to retrieve information from GraphHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only analysis of the codebase knowledge graph given a bug description or error message. It queries and returns ranked results (symbols, callers, callees, impact risk) but does not modify, execute, or delete anything. It explicitly replaces a chain of read/analysis operations (semantic_search → get_context → impact_analysis) with a single call, all of which are read operations.
From the tool's definition 'returns ranked candidate symbols enriched with callers, callees, and impact risk' — the tool retrieves and analyzes existing graph data without modifying anything
Documented attack patterns abuse exactly the kind of access debug_trace gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for debug_trace:
{
"version": "1",
"default": "deny",
"tools": {
"debug_trace": {}
}
}debug_trace 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.
One-shot debugging entry point. Given a bug description or error message, returns ranked candidate symbols enriched with callers, callees, and impact risk. Replaces the semantic_search → get_context → impact_analysis chain with a single call to save tokens. It is categorised as a Read tool in the GraphHub MCP Server, which means it retrieves data without modifying state.
Register the GraphHub MCP server in PolicyLayer and add a rule for debug_trace: 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 GraphHub. Nothing to install.
debug_trace 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 debug_trace 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 debug_trace. 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.
debug_trace is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.