approve_all_candidates · OpenMemBrain MCP: Risk & Policy

WHAT IT DOES

What approve_all_candidates does on OpenMemBrain

AI agents use approve_all_candidates 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_all_candidates needs a policy

This tool performs a write operation that creates or commits data (memory candidates) into persistent storage. While the blast radius is moderate—an agent could approve unwanted, incorrect, or noisy candidates into memory—the action is theoretically reversible (via rejection or deletion of approved items) and does not destroy data or execute arbitrary code.

From the tool's definition The tool description states it will 'Approve all pending memory candidates at once', which constitutes creating/modifying persistent memory entries.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_all_candidates Rate-limited

approve_all_candidates 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_all_candidates": {
      "limits": [
        {
          "counter": "approve_all_candidates_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_all_candidates

What does the approve_all_candidates tool do? +

Approve all pending memory candidates at once. Secret candidates are skipped. 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_all_candidates? +

Register the OpenMemBrain MCP server in PolicyLayer and add a rule for approve_all_candidates: 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_all_candidates? +

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

Can I rate-limit approve_all_candidates? +

Yes. Add a rate_limit block to the approve_all_candidates 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_all_candidates completely? +

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

approve_all_candidates 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.