Search conversations using semantic similarity (vector embeddings).
AI agents call semantic_search to retrieve information from Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries conversation history data through semantic search without side effects. It matches the Read category definition: "retrieves or queries data; no side effects (search, list, get, fetch)". The search operation over embeddings cannot modify, delete, or execute external operations.
From the tool's definition Tool description explicitly states it "Search[es] conversations using semantic similarity (vector embeddings)". The verb is "search", which is a read-only query operation. No modifications, deletions, executions, or financial transactions are possible.
Documented attack patterns abuse exactly the kind of access semantic_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Brain, and nothing reaches the server without passing your rules. This is the rule we recommend for semantic_search:
{
"version": "1",
"default": "deny",
"tools": {
"semantic_search": {}
}
}semantic_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.
Search conversations using semantic similarity (vector embeddings). It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.
Register the Brain MCP server in PolicyLayer and add a rule for semantic_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 Brain. Nothing to install.
semantic_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 semantic_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 semantic_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.
semantic_search is provided by the Brain MCP server (mordechaipotash/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Brain, 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.
34 Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.