recall_from_memory
AI agents call recall_from_memory to retrieve information from Vector Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name implies reading/querying stored memory data. The server is described as a long-term memory system for saving and recalling information, so 'recall' aligns with a Read operation. However, the empty description lowers confidence — there's no confirmation it cannot also modify state. Severity is medium because retrieved data may be sensitive personal or contextual information stored by the AI assistant.
From the tool's definition Tool name 'recall_from_memory' and server description 'recall information from files or free-form notes' suggest a retrieval operation.
Attacks that exploit this kind of access
recall_from_memory. It is categorised as a Read tool in the Vector Memory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vector Memory MCP Server MCP server in PolicyLayer and add a rule for recall_from_memory: 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 Vector Memory MCP Server. Nothing to install.
recall_from_memory 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_from_memory 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_from_memory. 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_from_memory is provided by the Vector Memory MCP Server MCP server (neerajg03/vector-memory). 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 →