Medium Risk

remember

Store a memory or piece of information. Use this to save facts, preferences, decisions, reasoning, or exploratory thinking. For facts and preferences, use telegraphic form —

How to control remember ↓

What remember does on Hippocampus

AI agents use remember to create or update resources in Hippocampus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hippocampus environment.

Medium Risk

Why remember needs a policy

The tool creates new records or modifies existing memory entries in a persistent storage system. This is a reversible write operation (data can be forgotten/deleted via sibling tools like 'forget' or 'update'). While it affects the AI's persistent context and decision-making, it does not directly execute external code, delete data irreversibly, or move financial resources.

From the tool's definition Tool description states 'Store a memory or piece of information' and 'save facts, preferences, decisions, reasoning' — explicit write operation that creates or modifies data in the knowledge graph.

Documented attack patterns abuse exactly the kind of access remember gives an agent:

How to control remember

PolicyLayer is an MCP gateway — it sits between your AI agents and Hippocampus, and nothing reaches the server without passing your rules. This is the rule we recommend for remember:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "remember": {
      "limits": [
        {
          "counter": "remember_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

remember stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Hippocampus — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about remember

What does the remember tool do? +

Store a memory or piece of information. Use this to save facts, preferences, decisions, reasoning, or exploratory thinking. For facts and preferences, use telegraphic form —. It is categorised as a Write tool in the Hippocampus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on remember? +

Register the Hippocampus 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 Hippocampus. Nothing to install.

What risk level is remember? +

remember is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit remember? +

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.

How do I block remember completely? +

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.

What MCP server provides remember? +

remember is provided by the Hippocampus MCP server (karrolcia/hippocampus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Hippocampus tool call.

Start from Hippocampus, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

11 Hippocampus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.