addToMCPMemory · MCP Memory MCP: Risk & Policy

WHAT IT DOES

What addToMCPMemory does on MCP Memory

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

WHY IT NEEDS A POLICY

Why addToMCPMemory needs a policy

This tool creates or modifies data persistently (Write category). Severity is medium because misuse could store sensitive user information, manipulate user preferences, or pollute memory with false data affecting future conversations, but the blast radius is limited to the memory layer without direct access to external systems or financial operations.

From the tool's definition Tool name 'addToMCPMemory' and description state it 'stores important information in a persistent memory layer', which creates or modifies data. The sibling tools include 'deleteMemory' and 'deleteNamespace', confirming this is a data storage system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

addToMCPMemory Rate-limited

addToMCPMemory 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": {
    "addToMCPMemory": {
      "limits": [
        {
          "counter": "addtomcpmemory_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 MCP Memory, so you can run agents against it safely.

FAQ

Questions about addToMCPMemory

What does the addToMCPMemory tool do? +

This tool stores important information in a persistent memory layer. Use it when: 1. User explicitly asks to remember something (. It is categorised as a Write tool in the MCP Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on addToMCPMemory? +

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

What risk level is addToMCPMemory? +

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

Can I rate-limit addToMCPMemory? +

Yes. Add a rate_limit block to the addToMCPMemory 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 addToMCPMemory completely? +

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

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