AI agents call free_social_media_search to retrieve information from Freesearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves social media search results without modifying, deleting, or executing code. The naming pattern and server purpose (free search functionality) confirm it as a Read operation. Confidence is slightly reduced due to empty description, but the pattern of sibling tools and server context provide strong inference.
From the tool's definition Tool name 'free_social_media_search' and server context (SearXNG search MCP server) indicate data retrieval; sibling tools (free_general_search, free_image_search, free_news_search, etc.) are all search/query operations with no side effects.
Documented attack patterns abuse exactly the kind of access free_social_media_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Freesearch, and nothing reaches the server without passing your rules. This is the rule we recommend for free_social_media_search:
{
"version": "1",
"default": "deny",
"tools": {
"free_social_media_search": {}
}
}free_social_media_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.
free_social_media_search. It is categorised as a Read tool in the Freesearch MCP Server, which means it retrieves data without modifying state.
Register the Freesearch MCP server in PolicyLayer and add a rule for free_social_media_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 Freesearch. Nothing to install.
free_social_media_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 free_social_media_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 free_social_media_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.
free_social_media_search is provided by the Freesearch MCP server (wzj177/mcp-server-freesearch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Freesearch, 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.
10 Freesearch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.