Search memories by semantic similarity and keyword match. Returns relevant stored information ranked by relevance.
AI agents call recall to retrieve information from Hippocampus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The recall tool is a pure read operation that searches and retrieves stored memories without creating, modifying, deleting, or executing any actions. It has minimal blast radius as misuse would only expose information the tool is designed to return.
From the tool's definition Tool description states it 'Search memories by semantic similarity and keyword match' and 'Returns relevant stored information ranked by relevance' — these are query/retrieval operations with no modification of data.
Documented attack patterns abuse exactly the kind of access recall gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hippocampus, and nothing reaches the server without passing your rules. This is the rule we recommend for recall:
{
"version": "1",
"default": "deny",
"tools": {
"recall": {}
}
} recall 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 memories by semantic similarity and keyword match. Returns relevant stored information ranked by relevance. It is categorised as a Read tool in the Hippocampus MCP Server, which means it retrieves data without modifying state.
Register the Hippocampus MCP server in PolicyLayer and add a rule for recall: 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 Hippocampus. Nothing to install.
recall 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 recall 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 recall. 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.
recall is provided by the Hippocampus MCP server (karrolcia/hippocampus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hippocampus, 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.
11 Hippocampus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.