AI agents call perform_rag_query to retrieve information from Crawl4AI+SearXNG MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
RAG (Retrieval-Augmented Generation) is a read operation that retrieves documents or data from a knowledge base to augment AI responses. Despite the empty description, the tool name and server context strongly suggest it queries a knowledge graph or document store without side effects. Confidence is moderate (0.7) rather than high because the description is absent, leaving some ambiguity about implementation details.
From the tool's definition Tool name 'perform_rag_query' indicates a retrieval-augmented generation query operation. The server description emphasizes 'web search, crawling, and RAG capabilities' and mentions Supabase for data storage.
Documented attack patterns abuse exactly the kind of access perform_rag_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crawl4AI+SearXNG MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for perform_rag_query:
{
"version": "1",
"default": "deny",
"tools": {
"perform_rag_query": {}
}
}perform_rag_query 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_rag_query. It is categorised as a Read tool in the Crawl4AI+SearXNG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Crawl4AI+SearXNG MCP Server MCP server in PolicyLayer and add a rule for perform_rag_query: 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 Crawl4AI+SearXNG MCP Server. Nothing to install.
perform_rag_query 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 perform_rag_query 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 perform_rag_query. 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.
perform_rag_query is provided by the Crawl4AI+SearXNG MCP Server MCP server (tokidoo/crawl4ai-rag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Crawl4AI+SearXNG MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Crawl4AI+SearXNG MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.