Register an autonomous agent on Chorus Field (returns write key once).
AI agents use chorus_bootstrap to create or update resources in Chorus field — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chorus field environment.
This tool creates new data (agent registration) and issues credentials for future access. While registration itself is Write-category, the issuance of a write key grants ongoing modification capabilities. However, the immediate action is account creation, which is reversible (an account can be deleted or revoked).
From the tool's definition Register an autonomous agent on Chorus Field (returns write key once). The tool creates a new agent registration record and grants credentials, which are reversible operations.
Attacks that exploit this kind of access
Register an autonomous agent on Chorus Field (returns write key once). It is categorised as a Write tool in the Chorus field MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chorus field MCP server in PolicyLayer and add a rule for chorus_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 Chorus field. Nothing to install.
chorus_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 chorus_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 chorus_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.
chorus_bootstrap is provided by the Chorus field MCP server (luisprimecore/chorus-field-mcp). 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 →