Perform a fast git grep inside the repository, allowing regex matching by default or substring search.
AI agents call search_code to retrieve information from Gread without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Full name of the repository (owner/name) |
path | string | — | Directory or file path to limit the search scope |
query | string | — | Search pattern or query to pass to git grep |
ignoreCase | boolean | — | Ignore case distinctions in both the PATTERN and the input files (-i) |
contextLines | number | — | Print num lines of output context (-C) |
fixedStrings | boolean | — | Use fixed strings for patterns (don’t interpret pattern as a regex) (-F) |
extendedRegexp | boolean | — | Use extended regular expressions (-E) |
Parameters from the server's own tool schema.
This tool only searches and retrieves code content using grep patterns. It has no capability to modify, delete, or execute code. The grep operation is a standard read-only search utility. Even though it operates on public GitHub repositories, the tool itself performs no side effects—it merely queries and returns matching code snippets.
From the tool's definition Tool performs 'fast git grep inside the repository, allowing regex matching by default or substring search' - this is a read-only search operation that retrieves code content without modification.
Risk signalsAccepts file system path (path) · Accepts freeform code/query input (query)
Documented attack patterns abuse exactly the kind of access search_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gread, and nothing reaches the server without passing your rules. This is the rule we recommend for search_code:
{
"version": "1",
"default": "deny",
"tools": {
"search_code": {}
}
}search_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Perform a fast git grep inside the repository, allowing regex matching by default or substring search. It is categorised as a Read tool in the Gread MCP Server, which means it retrieves data without modifying state.
search_code accepts 7 parameters: name, path, query, ignoreCase, contextLines, fixedStrings, extendedRegexp. The full parameter table on this page comes from the server's own tool schema.
Register the Gread MCP server in PolicyLayer and add a rule for search_code: 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 Gread. Nothing to install.
search_code 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 search_code 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 search_code. 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.
search_code is provided by the Gread MCP server (nitrofire-q/gread). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gread, 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.
5 Gread tools catalogued and risk-classified — across an index of 43,000+ MCP servers.