Create a new Tether agent. Requires TETHER_API_KEY. Returns the agent ID, name, and registration token (save it — it cannot be retrieved later). Optionally assign a verified domain.
AI agents use create_agent to create or update resources in Tether Name — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tether Name environment.
This tool creates new agents and generates registration tokens that serve as permanent credentials. While not destructive (the agent can be deleted via delete_agent), it modifies system state by creating persistent identity records. The token generation with explicit warning "save it — it cannot be retrieved later" indicates critical state creation.
From the tool's definition Tool description states "Create a new Tether agent" which creates and registers a new identity object. Returns registration credentials (agent ID, name, registration token) that cannot be retrieved later, indicating irreversible state creation.
Attacks that exploit this kind of access
Create a new Tether agent. Requires TETHER_API_KEY. Returns the agent ID, name, and registration token (save it — it cannot be retrieved later). Optionally assign a verified domain. It is categorised as a Write tool in the Tether Name MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tether Name MCP server in PolicyLayer and add a rule for create_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 Tether Name. Nothing to install.
create_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 create_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 create_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.
create_agent is provided by the Tether Name MCP server (tether-name-mcp-server). 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 →