AI agents use bootstrap 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.
This tool creates new persistent identity records and configuration files for AI agents. It is a Write operation because it generates new data structures that can typically be modified or replaced later. The severity is medium because misconfiguration of an agent identity could affect subsequent sessions and agent behavior, but the operation is reversible (identity can be re-initialized or updated).
From the tool's definition Tool description states it 'Initialize a new loom identity from scratch' and 'Generates IDENTITY.md, preferences.md' — clearly creates new files/data structures without reversibility constraints explicitly mentioned.
Attacks that exploit this kind of access
Initialize a new loom identity from scratch. Generates IDENTITY.md, preferences.md,. 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.
Register the Loom MCP server in PolicyLayer and add a rule for bootstrap: 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.
bootstrap is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the bootstrap 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 bootstrap. 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.
bootstrap 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 →