Back to blog
MPP
May 27, 20265 min readFacilitator

MPP for AI agents

MPP gives agents a structured problem+json payment negotiation path for paid HTTP services and marketplace capabilities.

Why it matters

Some buyer runtimes prefer an explicit problem+json challenge rather than pure HTTP 402 semantics. MPP lets those agents understand price, asset, and settlement requirements before retrying.

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 the MPP rail on the payable endpoint, returns machine-readable payment requirements, verifies settlement, forwards paid calls, and records MPP receipt context.

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

Choose MPP for clients that expect problem details, document the accepted asset and method, test both unpaid and paid requests, and list the endpoint under the seller capability.

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.

FAQ

Is MPP only for marketplace listings?

No. A private paid endpoint can use MPP without being listed publicly. Listing only adds discovery.

Can buyer-kit handle MPP?

Yes. Buyer-kit detects supported challenge shapes and can settle MPP endpoints when the buyer treasury has funds and policy allows the spend.

Building with Leash?

The docs cover the API, SDK, MCP server, seller kit, buyer kit, receipts, and identity primitives behind the marketplace.

Read docs