Low Risk

grep

grep

How to control grep ↓

What grep does on Polycodegraph

AI agents call grep to retrieve information from Polycodegraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why grep needs a policy

Grep is a classic read-only search tool that locates patterns in code or files. The server context ('code-graph MCP server') and sibling tools (list_directory, read_file) confirm a read-focused purpose. No description was provided, which slightly reduces confidence, but the tool name alone strongly implies a retrieval operation with no side effects.

From the tool's definition Tool named 'grep' with no description provided. Based on standard grep utility behavior, this retrieves/queries text patterns in files without modifying data.

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

How to control grep

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "grep": {}
  }
}

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

  1. Create a free account and register Polycodegraph — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about grep

What does the grep tool do? +

grep. It is categorised as a Read tool in the Polycodegraph MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on grep? +

Register the Polycodegraph 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 Polycodegraph. Nothing to install.

What risk level is grep? +

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

Can I rate-limit grep? +

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.

How do I block grep completely? +

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.

What MCP server provides grep? +

grep is provided by the Polycodegraph MCP server (smochan/polycodegraph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Polycodegraph tool call.

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

Free to start. No card required.

3 Polycodegraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.