Get a summarized profile of a user built from their memories — key topics, entity count, and a narrative summary. Use when you need a quick overview of what is known about a specific user before diving into their memories.
AI agents call get_memory_profile to retrieve information from Memsolus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is a Read operation as it retrieves and queries data without modifying or deleting anything. However, it accesses sensitive personal information (user profiles, memories, preferences, and relationships) stored in a semantic memory system.
From the tool's definition Tool retrieves and summarizes a user's stored memories including 'key topics, entity count, and a narrative summary' — it queries and returns sensitive personal data from a persistent memory system about a specific user.
Attacks that exploit this kind of access
Get a summarized profile of a user built from their memories — key topics, entity count, and a narrative summary. Use when you need a quick overview of what is known about a specific user before diving into their memories. It is categorised as a Read tool in the Memsolus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Memsolus MCP Server MCP server in PolicyLayer and add a rule for get_memory_profile: 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 Memsolus MCP Server. Nothing to install.
get_memory_profile 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_memory_profile 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_memory_profile. 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_memory_profile is provided by the Memsolus MCP Server MCP server (memsolus/mcp). 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 →