Search for files by pattern (e.g., *.js, *.py)
AI agents call fs_search_files to retrieve information from AI Code Review MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only discovers and lists files matching a pattern; it performs no creation, modification, deletion, or execution. The search operation is a safe, non-destructive query against the file system. While it may expose file paths and existence information, it does not alter state or trigger side effects, fitting squarely in the Read category with low blast radius.
From the tool's definition Tool description states it 'Search[es] for files by pattern' with examples like '*.js' and '*.py'. The name 'fs_search_files' and verb 'search' indicate file discovery with no modifications.
Attacks that exploit this kind of access
Search for files by pattern (e.g., *.js, *.py). It is categorised as a Read tool in the AI Code Review MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AI Code Review MCP Server MCP server in PolicyLayer and add a rule for fs_search_files: 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 AI Code Review MCP Server. Nothing to install.
fs_search_files 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 fs_search_files 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 fs_search_files. 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.
fs_search_files is provided by the AI Code Review MCP Server MCP server (namph-kozocom/review-code-mcp). 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 →