Step 1: Search memory. Returns index with IDs. Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy
AI agents call search to retrieve information from Claude Recall without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/retrieval operation that queries a memory store and returns results. It has no side effects, does not execute code, modify data, delete data, or move money. It is purely informational retrieval, making it a Read category tool. Severity is low because misuse would at worst expose previously stored context, which is the tool's intended purpose.
From the tool's definition The tool description states it "Returns index with IDs" in response to a search query. It searches memory without modifying, creating, or deleting any data.
Documented attack patterns abuse exactly the kind of access search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Recall, and nothing reaches the server without passing your rules. This is the rule we recommend for search:
{
"version": "1",
"default": "deny",
"tools": {
"search": {}
}
}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.
Step 1: Search memory. Returns index with IDs. Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy. It is categorised as a Read tool in the Claude Recall MCP Server, which means it retrieves data without modifying state.
Register the Claude Recall MCP server in PolicyLayer and add a rule for 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 Claude Recall. Nothing to install.
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 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 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.
search is provided by the Claude Recall MCP server (nhevers/moltbrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Claude Recall tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Claude Recall tools catalogued and risk-classified — across an index of 42,500+ MCP servers.