Search and retrieve memories
AI agents call recall to retrieve information from JauMemory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored information without modifying, deleting, or executing external operations. It is a straightforward read operation that queries the persistent memory system. No data is altered, destroyed, or financially impactful. Low severity due to limited blast radius — the worst outcome is disclosure of stored memories, which the user or agent already has authorization to access.
From the tool's definition Tool is named 'recall' with description 'Search and retrieve memories' — uses verbs 'search' and 'retrieve' which are query/read operations with no side effects.
Attacks that exploit this kind of access
Search and retrieve memories. It is categorised as a Read tool in the JauMemory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the JauMemory MCP Server 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 JauMemory MCP Server. 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 JauMemory MCP Server MCP server (jau-app/jaumemory-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →