Perform multiple web searches concurrently. Useful for comparing information from different queries or exploring related topics simultaneously.
AI agents call multi_search to retrieve information from SearXNG MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
multi_search is a read-only tool that queries and returns search results. It has no side effects: it does not create, modify, delete, or execute code. Even though it performs multiple concurrent searches, the operation is fundamentally a data retrieval action with no ability to alter state or trigger external operations. The local, privacy-focused nature and caching mechanisms do not elevate the risk category.
From the tool's definition Tool performs 'web searches' which retrieves information from a 'privacy-focused local SearXNG instance' with 'automatic result caching' and 'filtering options'.
Documented attack patterns abuse exactly the kind of access multi_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SearXNG MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for multi_search:
{
"version": "1",
"default": "deny",
"tools": {
"multi_search": {}
}
}multi_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.
Perform multiple web searches concurrently. Useful for comparing information from different queries or exploring related topics simultaneously. It is categorised as a Read tool in the SearXNG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SearXNG MCP Server MCP server in PolicyLayer and add a rule for multi_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 SearXNG MCP Server. Nothing to install.
multi_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 multi_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 multi_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.
multi_search is provided by the SearXNG MCP Server MCP server (pascalrjt/searxng-websearch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SearXNG MCP Server, 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.
3 SearXNG MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.