mcpField
M
Macaroon Network

Macaroon Network

Local
macaroonnetwork.comSearch0Updated 6w ago

About Macaroon Network

Macaroon Network is an MCP discovery router for agents searching and executing evidence-backed products in its marketplace. It combines free catalog and source information with paid x402 product execution, while leaving payment signing to the caller’s wallet infrastructure.

Key features

  1. 01Natural-language product search
  2. 02Feed freshness and hash metadata
  3. 03Category registry and product counts
  4. 04Live MCP server and transport discovery
  5. 05Reviewed source and rights records
  6. 06x402 USDC product execution

Use cases

  1. 01Find products matching an agent’s intent
  2. 02Check feed freshness before use
  3. 03Inspect reviewed sources and MCP availability
  4. 04Execute a paid product with caller-signed payment

MCP support

It exposes discovery, metadata, source, and execution tools to MCP clients. Paid execution returns an x402 challenge for the caller to sign and submit on retry.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"com-macaroonnetwork": {
"command": "uvx",
"args": [
"macaroonnetwork-mcp"
]
}
}
}
Run commanduvx macaroonnetwork-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimacaroonnetwork-mcp0.4.0

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitintegerNoMaximum number of results to return
intentstringYesNatural language description of what the agent needs. E.g. 'source-labelled Christian scripture evidence'
categorystringNoOptional canonical category id from macaroons_categories.

Details

From the project README

macaroonnetwork-mcp

MCP discovery router for Macaroon Network, a marketplace where agents find evidence-backed products and pay per successful query.

The payment rail exposed by this release is x402 using USDC on Base mainnet. The package never holds a wallet or signs a payment. It returns the exact x402 challenge for the caller's own wallet infrastructure to sign, then accepts that signed proof on the retry.

Tools

  • macaroons_search — search sale-ready products by natural-language intent. Free.
  • macaroons_metadata — retrieve free freshness and content-hash metadata for a feed target.
  • macaroons_categories — retrieve the canonical category registry and exact mapped-product counts. Free.
  • macaroons_discover_mcp — retrieve evidenced live Macaroon MCP servers and their transports. Free.
  • macaroons_sources — retrieve reviewed source and rights records, with explicit partial-coverage reporting. Free.
  • macaroons_execute — execute an x402 USDC product and receive the predicate-verified result and receipt.

Paying with x402

When a product needs payment, macaroons_execute returns an x402_payment_required result instead of hiding the challenge:

{
  "x402_payment_required": true,
  "resource_url": "https://api.macaroonnetwork.com/execute/...",
  "amount_atomic": "3000",
  "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
  "network": "eip155:8453",
  "pay_to": "0x33cc...",
  "extra_name": "USD Coin",
  "extra_version": "2",
  "max_timeout_seconds": 60,
  "x402_version": 2
}

Sign the exact payment described by the challenge with your own wallet or Coinbase CDP infrastructure. Then call macaroons_execute again with identical arguments plus payment_signature. x402 exact settlement uses one signed retry; there is no invoice-polling flow.

Install

pip install macaroonnetwork-mcp

Use with an MCP client

{
  "mcpServers": {
    "macaroonnetwork": {
      "command": "macaroonnetwork-mcp"
    }
  }
}

The default registry is https://api.macaroonnetwork.com. For local development, override it with MACAROONS_REGISTRY_URL.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.