Get all memories with hybrid cloud/cache intelligence and pagination support
AI agents call get_all_memories to retrieve information from r3 (Recall) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored memories from the system without creating, modifying, or deleting any data. It is fundamentally a read operation. However, severity is elevated to 'medium' because unrestricted access to all memories could expose sensitive personal data, conversation history, or private context that an AI agent shouldn't access without authorization.
From the tool's definition Tool name 'get_all_memories' and description 'Get all memories' indicate data retrieval without modification. The 'hybrid cloud/cache intelligence and pagination support' confirms read-only querying capabilities.
Attacks that exploit this kind of access
Get all memories with hybrid cloud/cache intelligence and pagination support. It is categorised as a Read tool in the r3 (Recall) MCP Server, which means it retrieves data without modifying state.
Register the r3 (Recall) MCP server in PolicyLayer and add a rule for get_all_memories: 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 r3 (Recall). Nothing to install.
get_all_memories 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 get_all_memories 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 get_all_memories. 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.
get_all_memories is provided by the r3 (Recall) MCP server (n3wth/r3). 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 →