Search for a phrase inside file contents recursively under a directory. Handles phrases split across lines (e.g. at 80-char wrap). Returns file, startLine, endLine, and matchText for each hit. Optionally filter by file glob pattern or exclude paths. Case-insensitive by default. Only works within ...
AI agents call find_in_files to retrieve information from FilesystemMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is a search/query operation that retrieves information about file contents without modifying, deleting, or executing anything. It matches the 'Read' category definition: retrieves or queries data with no side effects. The risk severity is low because misuse by an AI agent would only expose existing file content within already-allowed directories, with no destructive or systemic impact.
From the tool's definition The tool description explicitly states it 'Search[es] for a phrase inside file contents recursively under a directory' and 'Returns file, startLine, endLine, and matchText for each hit.' It performs queries and retrieval only, with no modification, deletion,…
Attacks that exploit this kind of access
Search for a phrase inside file contents recursively under a directory. Handles phrases split across lines (e.g. at 80-char wrap). Returns file, startLine, endLine, and matchText for each hit. Optionally filter by file glob pattern or exclude paths. Case-insensitive by default. Only works within allowed directories. It is categorised as a Read tool in the FilesystemMCP MCP Server, which means it retrieves data without modifying state.
Register the Filesystem MCP server in PolicyLayer and add a rule for find_in_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 FilesystemMCP. Nothing to install.
find_in_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 find_in_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 find_in_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.
find_in_files is provided by the Filesystem MCP server (rijadalisic/filesystemmcp). 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 →