Request a trust level change for a memory. Returns a confirmation token. Trust levels (1-5 integer scale): 1 = PUBLIC — anyone can see 2 = INTERNAL — friends/known users 3 = CONFIDENTIAL — trusted friends 4 = RESTRICTED — close/intimate contacts 5 = SECRET — owner only (default for new memories) ...
AI agents use remember_request_set_trust_level to create or update resources in Remember — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Remember environment.
This tool creates or modifies data reversibly. It changes the trust level and visibility permissions of memories in a multi-tenant system, which is a Write operation. Severity is high because misuse could expose confidential or restricted memories (trust levels 3-5) to unintended audiences (trust levels 1-2), affecting privacy of all users in the shared memory system.
From the tool's definition Tool description states it 'Request[s] a trust level change for a memory' and explicitly notes 'This is the ONLY way to change a memory.' It modifies the visibility/access control metadata of stored memories through a two-step confirmation process (request +…
Attacks that exploit this kind of access
Request a trust level change for a memory. Returns a confirmation token. Trust levels (1-5 integer scale): 1 = PUBLIC — anyone can see 2 = INTERNAL — friends/known users 3 = CONFIDENTIAL — trusted friends 4 = RESTRICTED — close/intimate contacts 5 = SECRET — owner only (default for new memories) After requesting, use remember_confirm with the returned token to apply the change. Lowering trust (e.g. 5→1) makes the memory MORE visible. Raising trust makes it LESS visible. This is the ONLY way to change a memory. It is categorised as a Write tool in the Remember MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Remember MCP server in PolicyLayer and add a rule for remember_request_set_trust_level: 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 Remember. Nothing to install.
remember_request_set_trust_level is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the remember_request_set_trust_level 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 remember_request_set_trust_level. 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.
remember_request_set_trust_level is provided by the Remember MCP server (@prmichaelsen/remember-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 →