Research a topic using Brave Search and Perplexity
AI agents call research_topic to retrieve information from Social Media 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 third-party search services (Brave Search, Perplexity) to gather information about a topic. It retrieves and presents data without creating, modifying, deleting, or executing code. The action is inherently read-only with no side effects. Severity is low because misuse would only result in retrieval of potentially irrelevant or sensitive information, not system compromise or data loss.
From the tool's definition Tool name 'research_topic' and description 'Research a topic using Brave Search and Perplexity' indicate retrieval of information from external search engines with no modification or deletion of data.
Documented attack patterns abuse exactly the kind of access research_topic gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Social Media MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for research_topic:
{
"version": "1",
"default": "deny",
"tools": {
"research_topic": {}
}
}research_topic 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.
Research a topic using Brave Search and Perplexity. It is categorised as a Read tool in the Social Media MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Social Media MCP Server MCP server in PolicyLayer and add a rule for research_topic: 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 Social Media MCP Server. Nothing to install.
research_topic 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 research_topic 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 research_topic. 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.
research_topic is provided by the Social Media MCP Server MCP server (tayler-id/social-media-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Social Media 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 Social Media MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.