AI agents call code_explain to retrieve information from Onion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs code analysis and explanation—purely informational retrieval with no side effects. It reads code, processes it, and returns explanatory output. No data is modified, executed, or destroyed. This is a classic Read operation similar to other AI analysis tools on the server (ai_classify, ai_extract, ai_summarize).
From the tool's definition Tool description: '解释代码的功能和逻辑，支持所有主流编程语言' (Explain the functionality and logic of code, supporting all mainstream programming languages). The tool analyzes and returns information about code without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
解释代码的功能和逻辑，支持所有主流编程语言。. It is categorised as a Read tool in the Onion MCP Server, which means it retrieves data without modifying state.
Register the Onion MCP server in PolicyLayer and add a rule for code_explain: 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_explain 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 code_explain 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_explain. 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_explain 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 →