AI agents call fd_search_content 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 tool retrieves and queries file contents without any side effects. It uses ripgrep to search within files and fd to navigate the filesystem, both of which are query-only operations. No data modification, deletion, or code execution is described.
From the tool's definition Tool performs 'content search using fd+ripgrep' with no modification or execution capabilities mentioned. Description emphasizes search speed (10-100x faster) but does not indicate write, delete, or command execution.
Attacks that exploit this kind of access
🔍 BLAZING CONTENT SEARCH: Lightning-fast code search using fd+ripgrep (10-100x faster than find -exec grep). 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_content: 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_content 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_content 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_content. 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_content 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 →