get_suggestions
AI agents call get_suggestions 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.
This tool queries the search engine for autocomplete suggestions, which is a read-only operation that retrieves data without modifying or deleting anything. No execution of code or external commands occurs. Low severity because suggestions are typically non-sensitive metadata used to assist users in refining searches.
From the tool's definition Tool named 'get_suggestions' on a SearXNG metasearch server; based on context with sibling tools (search, get_config, health_check), this retrieves autocomplete suggestions.
Attacks that exploit this kind of access
get_suggestions. 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 get_suggestions: 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.
get_suggestions 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 get_suggestions 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 get_suggestions. 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.
get_suggestions is provided by the SearXNG MCP Server MCP server (martinchen448/searxng-mcp-server). 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 →