Perform deep research across multiple search terms using ONLY Google. Aggregates results from multiple Google searches, scores them by relevance, and returns the most relevant content with duplicates removed. Args: search_terms (List[str]): List of search terms to research. The LLM should provide...
AI agents call deep_research_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 is a read-only tool that queries Google Search and processes results locally. It has no side effects, does not modify any data, and does not execute code or commands. The aggregation and scoring of results are passive data operations. Severity is low because misuse would at worst return irrelevant search results to an AI agent, with no destructive, financial, or operational consequences.
From the tool's definition Tool performs "deep research across multiple search terms using ONLY Google" and "returns the most relevant content" — it retrieves and aggregates search results with no capability to modify, delete, or execute external operations.
Documented attack patterns abuse exactly the kind of access deep_research_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 deep_research_google:
{
"version": "1",
"default": "deny",
"tools": {
"deep_research_google": {}
}
}deep_research_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.
Perform deep research across multiple search terms using ONLY Google. Aggregates results from multiple Google searches, scores them by relevance, and returns the most relevant content with duplicates removed. Args: search_terms (List[str]): List of search terms to research. The LLM should provide multiple related search queries for comprehensive coverage. num_results_per_term (int): Number of results to fetch per search term. top_k_per_term (int): Number of top scored results to keep per search term. include_urls (bool): Whether to include URLs in the results. Returns: Dict containing aggregated research results from all search terms (Google only), with duplicates removed. 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 deep_research_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.
deep_research_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 deep_research_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 deep_research_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.
deep_research_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.