code_generate · Onion MCP: Risk & Policy

WHAT IT DOES

What code_generate does on Onion

AI agents use code_generate to create or update resources in Onion — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Onion environment.

WHY IT NEEDS A POLICY

Why code_generate needs a policy

This tool generates new code artifacts based on natural language input. It creates new content (code) but does not execute it, delete anything, or involve financial transactions. The primary action is creation/writing of code. Severity is medium because generated code could be malicious or incorrect if misused, but the tool itself only produces text output.

From the tool's definition 根据自然语言描述生成代码 (Generate code from natural language description)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

code_generate Rate-limited

code_generate stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "code_generate": {
      "limits": [
        {
          "counter": "code_generate_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about code_generate

What does the code_generate tool do? +

根据自然语言描述生成代码。. It is categorised as a Write tool in the Onion MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on code_generate? +

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

What risk level is code_generate? +

code_generate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit code_generate? +

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

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

code_generate is provided by the Onion MCP server (onion-ai/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.