update_identity · Loom MCP: Risk & Policy

WHAT IT DOES

What update_identity does on Loom

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

WHY IT NEEDS A POLICY

Why update_identity needs a policy

The tool modifies an AI agent's persistent identity and preferences across sessions, which is a write operation. While the scope is limited to the agent's own self-model rather than external systems, this constitutes data modification.

From the tool's definition Tool name is 'update_identity' and description states 'Update your self-model or preferences' — this creates or modifies data (agent identity/preferences) reversibly without deletion or irreversible effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_identity Rate-limited

update_identity 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": {
    "update_identity": {
      "limits": [
        {
          "counter": "update_identity_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 Loom, so you can run agents against it safely.

FAQ

Questions about update_identity

What does the update_identity tool do? +

Update your self-model or preferences with section-level precision. It is categorised as a Write tool in the Loom MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_identity? +

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

What risk level is update_identity? +

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

Can I rate-limit update_identity? +

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

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

update_identity is provided by the Loom MCP server (jbarket/loom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.