Search for code and group results by file. Useful for understanding which files are most relevant.
AI agents call search_grouped to retrieve information from GraphHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a codebase knowledge graph and returns grouped search results. It has no side effects—it does not create, modify, delete, or execute code. It is purely informational, making it a Read operation with low severity since misuse would only retrieve information the user likely has legitimate access to.
From the tool's definition Tool name 'search_grouped' and description 'Search for code and group results by file' indicate data retrieval with no mutation. The verb 'search' and 'group results' are read-only operations on a knowledge graph.
Documented attack patterns abuse exactly the kind of access search_grouped gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for search_grouped:
{
"version": "1",
"default": "deny",
"tools": {
"search_grouped": {}
}
}search_grouped 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.
Search for code and group results by file. Useful for understanding which files are most relevant. It is categorised as a Read tool in the GraphHub MCP Server, which means it retrieves data without modifying state.
Register the GraphHub MCP server in PolicyLayer and add a rule for search_grouped: 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 GraphHub. Nothing to install.
search_grouped 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_grouped 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_grouped. 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_grouped is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, 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.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.