approve_memory_candidate · OpenMemBrain MCP: Risk & Policy

WHAT IT DOES

What approve_memory_candidate does on OpenMemBrain

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

WHY IT NEEDS A POLICY

Why approve_memory_candidate needs a policy

This tool creates or modifies project memory by approving and persisting a candidate entry. While the modification is reversible (memory can be updated or removed later via other tools like reject_memory_candidate), it definitively commits data to storage. This qualifies as Write rather than Read (which would be passive retrieval) or Destructive (which would be irreversible deletion).

From the tool's definition Tool description explicitly states 'persist it as local project memory,' which is a create/modify operation that writes data to persistent storage.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_memory_candidate Rate-limited

approve_memory_candidate 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": {
    "approve_memory_candidate": {
      "limits": [
        {
          "counter": "approve_memory_candidate_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 OpenMemBrain, so you can run agents against it safely.

FAQ

Questions about approve_memory_candidate

What does the approve_memory_candidate tool do? +

Approve a pending candidate and persist it as local project memory. It is categorised as a Write tool in the OpenMemBrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on approve_memory_candidate? +

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

What risk level is approve_memory_candidate? +

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

Can I rate-limit approve_memory_candidate? +

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

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

approve_memory_candidate is provided by the OpenMemBrain MCP server (mohamadalhusseinie/openmembrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.