Discover SearXNG instance capabilities.
AI agents call searxng_instance_info to retrieve information from Mcp Searxng without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about SearXNG instance capabilities. It is a lookup or metadata query operation with no side effects, modifications, or code execution. It falls squarely into the Read category. Severity is low because discovering public instance capabilities poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name is 'searxng_instance_info' and description states it 'Discover[s] SearXNG instance capabilities' — this queries metadata about a search engine instance without modifying any data or triggering external operations.
Attacks that exploit this kind of access
Discover SearXNG instance capabilities. It is categorised as a Read tool in the Mcp Searxng MCP Server, which means it retrieves data without modifying state.
Register the Mcp Searxng MCP server in PolicyLayer and add a rule for searxng_instance_info: 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 Searxng. Nothing to install.
searxng_instance_info 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 searxng_instance_info 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 searxng_instance_info. 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.
searxng_instance_info is provided by the Mcp Searxng MCP server (mcp-searxng). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →