Search conversation history, summaries, and facts for a topic. Use when the user asks about past conversations.
AI agents call recall to retrieve information from Claude Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries historical conversation data from Supabase storage without creating, modifying, or deleting any data. It has no side effects and serves purely to fetch information in response to user queries. This is a classic Read category operation with low severity since it only accesses stored data that the system is already maintaining.
From the tool's definition The tool description explicitly states 'Search conversation history, summaries, and facts' which is a retrieval operation. The verb 'search' and the context of querying stored data without modification indicate a read-only action.
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 Claude Memory, 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 conversation history, summaries, and facts for a topic. Use when the user asks about past conversations. It is categorised as a Read tool in the Claude Memory MCP Server, which means it retrieves data without modifying state.
Register the Claude Memory 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 Claude Memory. 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 Claude Memory MCP server (jordanl61/claude-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Memory, 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.
7 Claude Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.