Search for a phrase within a single file. Handles phrases split across lines (e.g. at 80-char wrap) by matching with whitespace normalization. Returns startLine, endLine, and matchText for each hit — use these directly with edit_file or read_lines. Optionally include surrounding context lines. On...
AI agents call find_in_file 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 performs a search/query operation that retrieves matching text locations from a file without modifying, deleting, or executing anything. It is purely informational and has no side effects. The severity is low because even if misused, the worst outcome is information disclosure of file contents that an agent could already read directly with other tools on this server.
From the tool's definition Tool name is 'find_in_file' and description states it 'Search[es] for a phrase within a single file' and 'Returns startLine, endLine, and matchText for each hit'.
Attacks that exploit this kind of access
Search for a phrase within a single file. Handles phrases split across lines (e.g. at 80-char wrap) by matching with whitespace normalization. Returns startLine, endLine, and matchText for each hit — use these directly with edit_file or read_lines. Optionally include surrounding context lines. 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_file: 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_file 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_file 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_file. 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_file 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 →