memory_store · Claude Memory MCP: Risk & Policy

WHAT IT DOES

What memory_store does on Claude Memory MCP

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

WHY IT NEEDS A POLICY

Why memory_store needs a policy

memory_store creates and persists new memory entries in the DuckDB backend. This is a write operation—it adds data reversibly (entries can later be deleted via memory_delete).

From the tool's definition Tool description: 'Store a new memory' indicates creation of new data records. The verb 'store' combined with 'auto-embedding, summary, entity extraction, and TTL' describes data creation and modification operations with no mention of deletion or reversal of…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_store Rate-limited

memory_store 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_store": {
      "limits": [
        {
          "counter": "memory_store_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Memory MCP, so you can run agents against it safely.

FAQ

Questions about memory_store

What does the memory_store tool do? +

Store a new memory with auto-embedding, summary, entity extraction, and TTL. It is categorised as a Write tool in the Claude Memory MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memory_store? +

Register the Claude Memory MCP server in PolicyLayer and add a rule for memory_store: 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 Claude Memory MCP. Nothing to install.

What risk level is memory_store? +

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

Can I rate-limit memory_store? +

Yes. Add a rate_limit block to the memory_store 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_store completely? +

Set action: deny in the PolicyLayer policy for memory_store. 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_store? +

memory_store is provided by the Claude Memory MCP server (navid-kianfar/claude-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.