AI agents call deep_research 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.
Deep research tools on a RAG server retrieve and query information without modifying data or triggering external side effects. This is a read-only operation typical of information retrieval systems. Confidence is slightly reduced (0.85 rather than 0.95) because the tool description is empty, but the server context and sibling tool names strongly indicate search/retrieval behavior.
From the tool's definition Tool name 'deep_research' and server description indicate web search capabilities. Sibling tools include 'deep_research_ddgs', 'deep_research_google', 'rag_search_ddgs', 'rag_search_google'—all querying/search operations.
Documented attack patterns abuse exactly the kind of access deep_research 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:
{
"version": "1",
"default": "deny",
"tools": {
"deep_research": {}
}
}deep_research 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.
deep_research. 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: 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 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 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. 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 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.