raw_query · code-intel MCP Server MCP: Risk & Policy

WHAT IT DOES

What raw_query does on code-intel MCP Server

AI agents invoke raw_query to trigger actions in code-intel MCP Server. 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 raw_query needs a policy

This tool executes user-supplied query strings against a graph backend. Even though described as 'simplified,' arbitrary query execution can expose sensitive code intelligence data, traverse unexpected graph paths, or (depending on backend permissions) perform write/delete operations. The most severe applicable category is Execute due to running dynamic queries whose effects depend on the arguments provided.

From the tool's definition 'Execute a simplified Cypher-like graph query' — the tool runs arbitrary query expressions against a graph database

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

raw_query Rate-limited

raw_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": {
    "raw_query": {
      "limits": [
        {
          "counter": "raw_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 code-intel MCP Server, so you can run agents against it safely.

FAQ

Questions about raw_query

What does the raw_query tool do? +

Execute a simplified Cypher-like graph query. Supports: name=\. It is categorised as a Execute tool in the code-intel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on raw_query? +

Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for raw_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 code-intel MCP Server. Nothing to install.

What risk level is raw_query? +

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

Can I rate-limit raw_query? +

Yes. Add a rate_limit block to the raw_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 raw_query completely? +

Set action: deny in the PolicyLayer policy for raw_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 raw_query? +

raw_query is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.