grep
AI agents call grep to retrieve information from Filesystem MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Grep is fundamentally a search/query tool that locates patterns in files and returns matching lines. It has no side effects on the filesystem. Within a sandboxed filesystem MCP server, grep would be restricted to allowed directories and returns data only. Even with arbitrary patterns, it cannot modify, delete, or execute code—only read and report. Low severity due to query-only nature and sandbox constraints.
From the tool's definition Tool named 'grep' with no description; standard grep behavior searches/queries file contents without modifying data. Context: sibling tools include read_text_file, list_directory, and directory_tree—all Read operations.
Attacks that exploit this kind of access
grep. It is categorised as a Read tool in the Filesystem MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Filesystem MCP Server MCP server in PolicyLayer and add a rule for grep: 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 Filesystem MCP Server. Nothing to install.
grep 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 grep 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 grep. 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.
grep is provided by the Filesystem MCP Server MCP server (preston-harrison/fs-mcp-py). 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 →