file_grep

THE RISK

Low Risk

Why file_grep needs a policy

file_grep performs pattern matching and retrieval of matching content from files. It does not modify, delete, or execute code—it only reads and returns results. Even within a containerized environment, grep-like operations are fundamentally read-only.

From the tool's definition Tool name 'file_grep' and description 'Search for regex patterns in files' indicate a search/query operation with no side effects. The verb 'search' is explicitly retrieval-focused.

Documented attack patterns abuse exactly the kind of access file_grep gives an agent:

POLICY

How to control file_grep

PolicyLayer is an MCP gateway — it sits between your AI agents and Docker MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for file_grep:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "file_grep": {}
  }
}

file_grep is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Docker MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Docker MCP Server tools

Execute execute_command Execute a shell command. Working directory: ${WORKSPACE} Execute send_input Send input to a running background process Write file_edit Replace text in a file using exact string matching. Use paths relative to ${WORKSPACE}. Re Write file_write Create or overwrite a file. Use paths relative to ${WORKSPACE}. Read the file first before Read check_process Check the status of a background process by its ID Read file_glob Find files by glob pattern (e.g., Read file_ls List files and directories. Use paths relative to ${WORKSPACE}. Read file_read Read a file

All 9 Docker MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about file_grep

What does the file_grep tool do? +

Search for regex patterns in files within ${WORKSPACE}. It is categorised as a Read tool in the Docker MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on file_grep? +

Register the Docker MCP Server MCP server in PolicyLayer and add a rule for file_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 Docker MCP Server. Nothing to install.

What risk level is file_grep? +

file_grep is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit file_grep? +

Yes. Add a rate_limit block to the file_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.

How do I block file_grep completely? +

Set action: deny in the PolicyLayer policy for file_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.

What MCP server provides file_grep? +

file_grep is provided by the Docker MCP Server MCP server (kenforthewin/docker-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Docker MCP Server tool call.

Start from Docker MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →