reject_memory_candidate · OpenMemBrain MCP: Risk & Policy

WHAT IT DOES

What reject_memory_candidate does on OpenMemBrain

AI agents use reject_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 reject_memory_candidate needs a policy

The tool modifies the state of a memory candidate by removing it from pending status. However, since the candidate is in a pending/draft state (not yet finalized), rejection is reversible — the candidate can be re-proposed later. This qualifies as Write rather than Destructive.

From the tool's definition Tool explicitly states 'Reject and remove a pending memory candidate' — 'remove' indicates deletion/modification of data, but 'pending' and 'candidate' suggest the data is not yet committed or irreversible.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reject_memory_candidate Rate-limited

reject_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": {
    "reject_memory_candidate": {
      "limits": [
        {
          "counter": "reject_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 reject_memory_candidate

What does the reject_memory_candidate tool do? +

Reject and remove a pending memory candidate. 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 reject_memory_candidate? +

Register the OpenMemBrain MCP server in PolicyLayer and add a rule for reject_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 reject_memory_candidate? +

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

Can I rate-limit reject_memory_candidate? +

Yes. Add a rate_limit block to the reject_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 reject_memory_candidate completely? +

Set action: deny in the PolicyLayer policy for reject_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 reject_memory_candidate? +

reject_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.