Trace upstream callers of a known workspace symbol for impact analysis before changing, renaming, or removing shared code. Resolve path with code.find_symbol first; use recursive mode for shared APIs. Language filters: ${SUPPORTED_LANGUAGE_FILTERS}.
AI agents call code.trace_callers to retrieve information from Navigation Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and queries caller relationships in a codebase to enable impact analysis. It performs structured inspection of symbol relationships without modifying code, executing external operations, or triggering side effects. The explicit mention of 'before changing, renaming, or removing' indicates this is a read-only analysis tool designed to inform decisions, not execute them.
From the tool's definition Trace upstream callers of a known workspace symbol for impact analysis before changing, renaming, or removing shared code.
Attacks that exploit this kind of access
Trace upstream callers of a known workspace symbol for impact analysis before changing, renaming, or removing shared code. Resolve path with code.find_symbol first; use recursive mode for shared APIs. Language filters: ${SUPPORTED_LANGUAGE_FILTERS}. It is categorised as a Read tool in the Navigation Agent MCP Server, which means it retrieves data without modifying state.
Register the Navigation Agent MCP server in PolicyLayer and add a rule for code.trace_callers: 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 Navigation Agent. Nothing to install.
code.trace_callers 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 code.trace_callers 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 code.trace_callers. 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.
code.trace_callers is provided by the Navigation Agent MCP server (j0k3r-dev-rgl/navigation-agent-mcp). 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 →