AI agents call code_search to retrieve information from LuzzyTool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
code_search performs read-only operations: searching for patterns, listing matching lines, and returning context. It uses ripgrep or Python regex matching to retrieve data without side effects. No creation, modification, deletion, or execution of arbitrary code occurs.
From the tool's definition Tool description states it 'searches code content in directories' (搜索代码内容) and 'returns matching lines and context' (返回匹配行及上下文).
Attacks that exploit this kind of access
【必须调用】在目录中搜索代码内容，支持正则表达式，返回匹配行及上下文。优先使用 ripgrep（更快），不可用时回退纯 Python。当需要查找函数定义、变量引用、特定代码模式时使用。支持文件类型过滤、大小写控制、全词匹配。. It is categorised as a Read tool in the LuzzyTool MCP Server, which means it retrieves data without modifying state.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for code_search: 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 LuzzyTool. Nothing to install.
code_search 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_search 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_search. 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_search is provided by the LuzzyTool MCP server (luzzymeow/luzzytool). 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 →