build_callgraph · JavaSinkTracer MCP: Risk & Policy

WHAT IT DOES

What build_callgraph does on JavaSinkTracer MCP

AI agents invoke build_callgraph to trigger actions in JavaSinkTracer MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why build_callgraph needs a policy

This tool actively processes and analyzes an entire Java project's codebase to construct a call graph. It is not a simple read/query of existing data — it executes a static analysis pass over all classes and methods to build a new relational structure. This constitutes an Execute-level operation (running an analysis engine).

From the tool's definition 构建Java项目的函数调用关系图(Call Graph)。分析项目中所有类和方法的调用关系 — 'builds' a call graph by analyzing all classes and methods, triggering active analysis/processing of source code across the project

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

build_callgraph Rate-limited

build_callgraph stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "build_callgraph": {
      "limits": [
        {
          "counter": "build_callgraph_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches JavaSinkTracer MCP, so you can run agents against it safely.

FAQ

Questions about build_callgraph

What does the build_callgraph tool do? +

构建Java项目的函数调用关系图(Call Graph)。分析项目中所有类和方法的调用关系。. It is categorised as a Execute tool in the JavaSinkTracer MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on build_callgraph? +

Register the JavaSinkTracer MCP server in PolicyLayer and add a rule for build_callgraph: 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 JavaSinkTracer MCP. Nothing to install.

What risk level is build_callgraph? +

build_callgraph is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit build_callgraph? +

Yes. Add a rate_limit block to the build_callgraph 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.

How do I block build_callgraph completely? +

Set action: deny in the PolicyLayer policy for build_callgraph. 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.

What MCP server provides build_callgraph? +

build_callgraph is provided by the JavaSinkTracer MCP server (zacarx/javasinktracer_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.