Trace the full call chain for an endpoint path. Shows controller → service → repository.
AI agents call trace_endpoint to retrieve information from Spring Api Intel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static code analysis to retrieve and display call chain information about a Spring Boot endpoint. It queries internal code structure and relationships but does not execute the application, modify code, delete data, or trigger external operations. The operation is read-only with no reversible or irreversible side effects, making it a Read category tool.
From the tool's definition Tool is described as 'Trace the full call chain for an endpoint path' which retrieves and analyzes code structure through static analysis without executing code or modifying data.
Attacks that exploit this kind of access
Trace the full call chain for an endpoint path. Shows controller → service → repository. It is categorised as a Read tool in the Spring Api Intel MCP Server, which means it retrieves data without modifying state.
Register the Spring Api Intel MCP server in PolicyLayer and add a rule for trace_endpoint: 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 Spring Api Intel. Nothing to install.
trace_endpoint 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_endpoint 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_endpoint. 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_endpoint is provided by the Spring Api Intel MCP server (mparth14/spring-api-intel-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 →