Onboard an agent that acts on behalf of controller_did.
AI agents use onboard_delegated_agent to create or update resources in Tenzro Ledger MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tenzro Ledger MCP environment.
This tool creates/registers a new delegated agent identity authorized to act on behalf of a controller DID. It is a Write operation (creating a new agent record/identity), but carries high severity because it grants an agent authority to act on behalf of another identity, enabling potential privilege escalation or unauthorized actions if misused.
From the tool's definition Onboard an agent that acts on behalf of ``controller_did``
Attacks that exploit this kind of access
Onboard an agent that acts on behalf of controller_did. It is categorised as a Write tool in the Tenzro Ledger MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tenzro Ledger MCP server in PolicyLayer and add a rule for onboard_delegated_agent: 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 Tenzro Ledger MCP. Nothing to install.
onboard_delegated_agent 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 onboard_delegated_agent 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 onboard_delegated_agent. 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.
onboard_delegated_agent is provided by the Tenzro Ledger MCP server (https://canton-mcp.tenzro.network/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 →