run_cpgql_query · CodeBadger MCP: Risk & Policy

WHAT IT DOES

What run_cpgql_query does on CodeBadger

AI agents invoke run_cpgql_query to trigger actions in CodeBadger. 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 run_cpgql_query needs a policy

This tool executes arbitrary queries (CPG QL or similar) against a codebase analysis engine. While the queries themselves analyze rather than modify code, the execution model allows an AI agent to run unvalidated analysis queries that could be resource-intensive, return sensitive taint/vulnerability data, or cause denial-of-service.

From the tool's definition Tool named 'run_cpgql_query' with no description; context indicates it executes queries against a Code Property Graph (Joern), enabling 'code browsing, security taint analysis, call graph exploration, and dataflow tracking through natural language queries.'…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_cpgql_query Rate-limited

run_cpgql_query 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": {
    "run_cpgql_query": {
      "limits": [
        {
          "counter": "run_cpgql_query_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 CodeBadger, so you can run agents against it safely.

FAQ

Questions about run_cpgql_query

What does the run_cpgql_query tool do? +

run_cpgql_query. It is categorised as a Execute tool in the CodeBadger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_cpgql_query? +

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

What risk level is run_cpgql_query? +

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

Can I rate-limit run_cpgql_query? +

Yes. Add a rate_limit block to the run_cpgql_query 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 run_cpgql_query completely? +

Set action: deny in the PolicyLayer policy for run_cpgql_query. 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 run_cpgql_query? +

run_cpgql_query is provided by the CodeBadger MCP server (lekssays/codebadger). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.