edit_memory · OmniHub MCP: Risk & Policy

WHAT IT DOES

What edit_memory does on OmniHub

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

WHY IT NEEDS A POLICY

Why edit_memory needs a policy

This tool modifies stored memories without permanently deleting them, making it a Write operation. The severity is medium because editing memories could corrupt or overwrite important developer insights, but the action is reversible by editing again. Confidence is high because the description clearly indicates the tool's function is to edit/modify existing records.

From the tool's definition Tool name 'edit_memory' and description 'Edits the content (and optionally category) of an existing memory by ID' explicitly indicate modification of existing data in a reversible manner.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

edit_memory Rate-limited

edit_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": {
    "edit_memory": {
      "limits": [
        {
          "counter": "edit_memory_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 OmniHub, so you can run agents against it safely.

FAQ

Questions about edit_memory

What does the edit_memory tool do? +

Edits the content (and optionally category) of an existing memory by ID. It is categorised as a Write tool in the OmniHub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on edit_memory? +

Register the OmniHub MCP server in PolicyLayer and add a rule for edit_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 OmniHub. Nothing to install.

What risk level is edit_memory? +

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

Can I rate-limit edit_memory? +

Yes. Add a rate_limit block to the edit_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 edit_memory completely? +

Set action: deny in the PolicyLayer policy for edit_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 edit_memory? +

edit_memory is provided by the OmniHub MCP server (malharrrr/omnihub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.