AI agents call fd_search to retrieve information from Fd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a file search tool that retrieves/queries file system data without modifying, deleting, or executing code. It enables navigation and discovery (Read category). Severity is low because file search alone poses minimal risk—an AI could inefficiently enumerate files, but this is easily bounded and causes no side effects.
From the tool's definition Tool name 'fd_search' and description indicate fast file search capabilities. The sibling tools include 'fd_search_content' (searching file contents) and 'fd_recent_files' (listing files), all non-mutating operations.
Attacks that exploit this kind of access
⚡ FAST FILE SEARCH: 5-10x faster than. It is categorised as a Read tool in the Fd MCP Server, which means it retrieves data without modifying state.
Register the Fd MCP server in PolicyLayer and add a rule for fd_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 Fd. Nothing to install.
fd_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 fd_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 fd_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.
fd_search is provided by the Fd MCP server (thhart/fd-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 →