About PennyRail Transaction Router
PennyRail is a transaction router for agent capabilities. It supports machine-readable capability discovery and x402 payment flows, routing payment to the selected execution URL.
Key features
- 01Machine-readable OpenAPI and x402 discovery
- 02Capability routes and templates
- 03Base USDC x402 settlement
- 04Agent402 demand intelligence
- 05the402 catalog and request bidding
- 06Optional OpenAI-backed capabilities
Use cases
- 01Discovering paid agent capabilities
- 02Selecting an execution endpoint for payment
- 03Publishing reusable capability routes
- 04Reviewing demand and revenue signals
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://pennyrail.vercel.app/api/mcpclaude mcp add --transport http clay-swartz-pennyrail https://pennyrail.vercel.app/api/mcp{"mcpServers":{"clay-swartz-pennyrail":{"type":"http","url":"https://pennyrail.vercel.app/api/mcp"}}}Open in Cursor{"servers":{"clay-swartz-pennyrail":{"type":"http","url":"https://pennyrail.vercel.app/api/mcp"}}}Open in VS Code{"mcpServers":{"clay-swartz-pennyrail":{"type":"http","url":"https://pennyrail.vercel.app/api/mcp"}}}{"mcpServers":{"clay-swartz-pennyrail":{"serverUrl":"https://pennyrail.vercel.app/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEPennyRail
PennyRail is an autonomous machine-commerce yield engine: observe paid agent demand, identify monetizable capability gaps, publish the smallest reliable solution, charge per machine call, distribute it across agent-buying surfaces, and keep expanding the portfolio around proven demand.
Current build — v36 Revenue Broker
Current revenue loop:
PAID DEMAND → MAP/GAP → BUILD REUSABLE PRIMITIVE → PRICE → PUBLISH → SELL/BID → MEASURE → MULTIPLY
The production stack includes:
- Base USDC x402 settlement with the proven Coinbase facilitator integration
- 47 original factory capabilities plus proven-demand templates
- dynamic revenue-product routes and machine-readable OpenAPI/x402 discovery
- paid Agent402 Bestsellers intelligence every six hours (Demand Radar disabled while its upstream itemized feed is empty)
- x402scan registration and x402 List review submission
- the402 provider/catalog/request-bidding integration
- optional OpenAI upstream broker capabilities, including live web search
- private Radar dashboard with on-chain outside-revenue tracking, remembered admin access and one-click JSON copying
See README_REVENUE_BROKER_V36.md for the current revenue build. Historical version notes are intentionally preserved in the versioned README files.
Production secrets
Secrets belong in Vercel Production environment variables only. Never commit admin tokens, wallet credentials, provider API keys, webhook secrets or OpenAI keys to the repository.
Operating objective
Maximize aggregate machine-commerce gross profit across many tiny transactions. Current internal target: at least $1,000/day / $30,000/month, with no architecture ceiling. This is a target, not a guarantee.
Comments
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.