Autocomplete search query suggestions.
AI agents call searxng_search_suggestions 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 autocomplete suggestions for search queries. It queries data from the SearXNG instance and returns suggestions without causing side effects, data modification, code execution, or deletion. The operation is read-only and safe from misuse — worst case, an agent receives irrelevant suggestions. No destructive, financial, or execution capabilities are present.
From the tool's definition Tool name 'searxng_search_suggestions' and description 'Autocomplete search query suggestions' indicate retrieval of suggestion data without modification or execution.
Attacks that exploit this kind of access
Autocomplete search query suggestions. 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_search_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 Mcp Searxng. Nothing to install.
searxng_search_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 searxng_search_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 searxng_search_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.
searxng_search_suggestions 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 →