AI agents call heal_code to retrieve information from Open Code Review without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The description 'Load a file' implies reading/loading file contents, which is a Read operation. However, the tool name 'heal_code' strongly suggests it may modify or fix code, which would be Write or higher. The description is uninformative and contradicts the tool name, so confidence is low.
From the tool's definition Tool description says only 'Load a file', which suggests a read operation
Documented attack patterns abuse exactly the kind of access heal_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Open Code Review, and nothing reaches the server without passing your rules. This is the rule we recommend for heal_code:
{
"version": "1",
"default": "deny",
"tools": {
"heal_code": {}
}
}heal_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load a file. It is categorised as a Read tool in the Open Code Review MCP Server, which means it retrieves data without modifying state.
Register the Open Code Review MCP server in PolicyLayer and add a rule for heal_code: 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 Open Code Review. Nothing to install.
heal_code is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the heal_code 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 heal_code. 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.
heal_code is provided by the Open Code Review MCP server (raye-deng/open-code-review). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Open Code Review, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Open Code Review tools catalogued and risk-classified — across an index of 43,000+ MCP servers.