propose_memory

Queue an uncertain or agent-generated memory proposal for review.

SERVERMapi Agent Memory SOURCEcabo0m/mapi-agent-memory

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mapi-agent-memory/propose-memory.md

WHAT IT DOES

What propose_memory does on Mapi Agent Memory

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

RISK

Why propose_memory is rated Medium

This tool writes a new memory proposal to a review queue. It creates a pending record that awaits approval, which is a reversible write operation (the proposal can be rejected/removed). It does not immediately execute, delete, or involve financial actions. Severity is medium because submitting malicious or misleading proposals into a governance queue could influence future agent behavior if approved.

From the tool's definition Queue an uncertain or agent-generated memory proposal for review

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs propose_memory safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mapi Agent Memory, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For propose_memory, this is the rule to start with:

propose_memory Rate-limited

propose_memory 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": {
    "propose_memory": {
      "limits": [
        {
          "counter": "propose_memory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mapi Agent Memory, apply this rule, and every propose_memory call is checked against it from then on.

FAQ

Questions about propose_memory

What does the propose_memory tool do? +

Queue an uncertain or agent-generated memory proposal for review. It is categorised as a Write tool in the Mapi Agent 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 propose_memory? +

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

What risk level is propose_memory? +

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

Can I rate-limit propose_memory? +

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

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

propose_memory is provided by the Mapi Agent Memory MCP server (cabo0m/mapi-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mapi Agent Memory, and thousands of servers like it.

This server

All 252 Mapi Agent Memory tools →

Across the catalogue

team_manager_write_memory on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →