AI agents call rag_search_google to retrieve information from Mcp Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to perform web search queries via Google, consistent with RAG (Retrieval-Augmented Generation) retrieval operations. Web search is a read-only operation that retrieves data without modifying, executing code, deleting data, or moving funds.
From the tool's definition Tool name 'rag_search_google' indicates a search operation. Server description states it is a 'RAG-like web search model context protocol server.' Sibling tools include 'rag_search_ddgs' and 'deep_research' variants, all consistent with information retrieval.
Documented attack patterns abuse exactly the kind of access rag_search_google gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for rag_search_google:
{
"version": "1",
"default": "deny",
"tools": {
"rag_search_google": {}
}
}rag_search_google 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.
rag_search_google. It is categorised as a Read tool in the Mcp Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Mcp Local Rag MCP server in PolicyLayer and add a rule for rag_search_google: 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 Mcp Local Rag. Nothing to install.
rag_search_google 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 rag_search_google 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 rag_search_google. 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.
rag_search_google is provided by the Mcp Local Rag MCP server (nkapila6/mcp-local-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Mcp Local Rag tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Mcp Local Rag tools catalogued and risk-classified — across an index of 42,500+ MCP servers.