AI agents use code_fix 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.
This tool modifies/rewrites code to fix bugs. It creates or modifies data (source code) reversibly — the output is corrected code. It doesn't execute the code or delete anything irreversibly, so Write is the most appropriate category. Severity is medium because an AI agent could introduce unintended changes to source code.
From the tool's definition 修复代码中的错误 (Fix errors in code)
Attacks that exploit this kind of access
修复代码中的错误，可提供错误信息以提高准确性。. 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.
Register the Onion MCP server in PolicyLayer and add a rule for code_fix: 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.
code_fix is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the code_fix 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 code_fix. 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.
code_fix 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.
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 →