AI agents call identity to retrieve information from Loom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves/loads persistent identity data and returns it. This is a read operation with no side effects — it fetches the agent's stored identity and creed without modifying any state.
From the tool's definition Load the persistent identity for this agent. Returns the terminal creed
Attacks that exploit this kind of access
Load the persistent identity for this agent. Returns the terminal creed. It is categorised as a Read tool in the Loom MCP Server, which means it retrieves data without modifying state.
Register the Loom MCP server in PolicyLayer and add a rule for 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.
identity is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →