add_message

THE RISK

Medium Risk

Why add_message needs a policy

This tool performs a reversible write operation—adding messages to a memory store. It creates new records in the dialogue history without deleting or modifying existing data. The blast radius is low because incorrect message storage is easily corrected by updating or re-recording. It does not execute arbitrary code, delete data irreversibly, or involve financial transactions.

From the tool's definition Tool description indicates it saves dialogue history (add_message), which is a write operation that creates/stores data. The trigger mechanism shows it 'saves' conversation data after answers, and can be 'invoked' to record user intent.

Risk signalsBulk/mass operation — affects multiple targets

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

POLICY

How to control add_message

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

policy.json

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

add_message 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.

Create a free account and register MemOS — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MemOS tools

Destructive delete_kb_documents Trigger: Use when specific documents in a Knowledge Base should be removed. Purpose: Del Destructive delete_memory Trigger: User explicitly asks to delete memories. Purpose: Delete memories by ID. STRI Destructive remove_knowledge_base Trigger: User requests to remove a Knowledge Base from the project. Purpose: Remove a Kn Write add_feedback Trigger: User wants to MODIFY/UPDATE memories, OR as the final step of a DELETION workflow Write add_kb_document Trigger: Use when the user provides document content, a file URL, or a local file path to Write create_knowledge_base Trigger: When the user asks to create a project-specific or domain-specific Read get_kb_documents Trigger: Use to retrieve detailed information about specific documents in a Knowledge Base Read get_user_profile Trigger: MANDATORY for queries like

All 10 MemOS tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about add_message

What does the add_message tool do? +

Trigger: 1. AUTO-INVOKED: After every answer to save dialogue history. 2. USER INTENT: When user explicitly wants to. It is categorised as a Write tool in the MemOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_message? +

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

What risk level is add_message? +

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

Can I rate-limit add_message? +

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

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

add_message is provided by the MemOS MCP server (memtensor/memos-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MemOS tool call.

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

CHECK YOUR STACK →