Show how one symbol reaches another: the connecting call sub-graph from
AI agents call trace to retrieve information from Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'trace' tool is purely informational, showing call graph relationships between symbols. It retrieves and displays data about code structure (call chains, dependencies) with no side effects, no code execution, no data modification, and no destructive operations. This is a classic Read category tool used for code analysis and understanding program flow.
From the tool's definition Tool description indicates 'Show how one symbol reaches another: the connecting call sub-graph from' — a retrieval/query operation that visualizes code dependencies and call paths without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access trace gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for trace:
{
"version": "1",
"default": "deny",
"tools": {
"trace": {}
}
}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.
Show how one symbol reaches another: the connecting call sub-graph from. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Local Rag MCP server in PolicyLayer and add a rule for 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 Local Rag. Nothing to install.
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 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 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.
trace is provided by the Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, 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.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.