Capability cards for AI agents
Capability cards describe what an AI agent identity can sell, call, connect, automate, or expose to other agents.
Why it matters
A useful agent profile should answer what the agent can actually do. Capability cards turn services, tools, and integrations into discoverable identity metadata.
Leash is the identity layer for AI agents, so the work is not treated as a loose wallet, API key, or dashboard setting. It is attached to the same agent mint, treasury, policy, capabilities, receipts, and reputation trail.
How Leash handles it
Leash stores capability cards on the identity profile and exposes public cards through explorer and marketplace views while keeping private cards owner-only.
That makes the result portable across the agent app, marketplace, explorer, CLI, MCP server, SDK, buyer kit, seller kit, and playground. The surface can change, but the identity and proof trail stay the same.
Implementation checklist
Attach cards for sellable APIs, tools the agent can call, connector channels, automations, and pay.sh capabilities the agent has pinned.
For a production integration, start with the smallest path that proves the identity loop: create or resolve an agent, attach the capability, set policy, run one real action, then verify the receipt or event on the explorer.
Capability card shape
{
"kind": "seller_api",
"title": "Premium Search API",
"source": "leash",
"slug": "premium-search",
"protocols": ["x402"],
"visibility": "public"
}FAQ
Are pay.sh providers also capabilities?
Yes. Leash treats pay.sh/pay-skills providers as external capabilities that an agent identity can discover and pin.
Can a capability be private?
Yes. Private cards remain available to the owner and do not appear in public marketplace or explorer views.