Register and publish a verified .agt agent identity
The agent's name is registered on-chain, its manifest is signed and hosted, and all endpoints are verified as live, establishing a trusted, verifiable identity for the agent.
How it works
Moves money or places ordersSoftware development
The agent uses the agt CLI to check name availability, register the name via a USDC payment on Polygon, initialize and fill out the manifest (including MCP and A2A endpoints), sign the manifest using the user's wallet or a secure keyfile, publish the manifest to a host, and finally verify that the on-chain records match the signed manifest and that endpoints are reachable.
Prompt
Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.
Prompt for Register and publish a verified .agt agent identity
Register the agent name 'myagent' for 1 year, initialize its manifest with the MCP endpoint 'https://myagent.example/mcp', publish the signed manifest, and verify the registration.MCP servers it needs
Source
The vendor page this playbook is drawn from, and the passage that supports it.
The agt command takes a name from search to a verified agent in a terminal: register it, write and sign its manifest, host it, set the on-chain records, and check the result.Register and publish from the command line — .agt Documentation