AI agents call global_search to retrieve information from CodeGraphMCPServer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation across a codebase using GraphRAG, which is a retrieval and analysis capability. It retrieves or queries data without modifying, deleting, or executing anything. The operation is purely informational and read-only, fitting the 'Read' category. Severity is low because misuse would only surface incorrect search results, with no destructive or system-altering consequences.
From the tool's definition Tool name is 'global_search' and description states 'Search across all communities using GraphRAG'. The verb 'search' and the read-only nature of querying a code graph indicate data retrieval with no side effects.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access global_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraphMCPServer, and nothing reaches the server without passing your rules. This is the rule we recommend for global_search:
{
"version": "1",
"default": "deny",
"tools": {
"global_search": {}
}
}global_search 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 across all communities using GraphRAG. It is categorised as a Read tool in the CodeGraphMCPServer MCP Server, which means it retrieves data without modifying state.
Register the CodeGraphMCPServer MCP server in PolicyLayer and add a rule for global_search: 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 CodeGraphMCPServer. Nothing to install.
global_search 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 global_search 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 global_search. 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.
global_search is provided by the CodeGraphMCPServer MCP server (nahisaho/codegraphmcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraphMCPServer, 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.
14 CodeGraphMCPServer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.