Store something in memory. Use for user preferences, project patterns, solutions, concepts.
AI agents use remember to create or update resources in Oceanir Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Oceanir Memory environment.
The tool explicitly stores/creates data in a persistent memory system. It is reversible (a 'forget' sibling tool exists), so it qualifies as Write rather than Destructive. Medium severity because a misuse could pollute the AI agent's long-term memory with incorrect or malicious knowledge, affecting future sessions.
From the tool's definition 'Store something in memory' — creates/writes new data (preferences, patterns, solutions, concepts) into the persistent knowledge graph
Attacks that exploit this kind of access
Store something in memory. Use for user preferences, project patterns, solutions, concepts. It is categorised as a Write tool in the Oceanir Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Oceanir Memory MCP server in PolicyLayer and add a rule for remember: 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 Oceanir Memory. Nothing to install.
remember 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 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. 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 is provided by the Oceanir Memory MCP server (oceanir/oceanir-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 →