memory_profile

Synthesize a coherent profile from preference and fact memories using LLM. Cached for 24h, auto-refreshed when preferences change. Returns markdown profile.

Server Mementos @hasna/mementos
Category Read
Risk class Low
Parameters 00 required

What memory_profile does on Mementos

AI agents call memory_profile to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why memory_profile needs a policy

This tool retrieves and processes stored memories to generate a synthesized profile document. It performs no data mutations, deletions, or external side effects. Auto-refresh on preference changes is an internal state management detail, not a destructive operation. The output is informational and the tool has minimal blast radius if misused by an agent.

From the tool's definition Tool synthesizes and returns a profile from existing memories; 'Returns markdown profile' indicates output-only operation with no modification or deletion of underlying data. Caching behavior confirms read-only nature.

Questions about memory_profile

What does the memory_profile tool do? +

Synthesize a coherent profile from preference and fact memories using LLM. Cached for 24h, auto-refreshed when preferences change. Returns markdown profile. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory_profile? +

Register the Mementos MCP server in PolicyLayer and add a rule for 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 Mementos. Nothing to install.

What risk level is memory_profile? +

memory_profile is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit memory_profile? +

Yes. Add a rate_limit block to the 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.

How do I block memory_profile completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides memory_profile? +

memory_profile is provided by the Mementos MCP server (@hasna/mementos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.