Skip to main content
Glama

Dark Money MCP Server

Cashback routing for AI agents, over the Model Context Protocol.

Dark Money is a cashback club built for the agent era. When a human is about to buy something online, their agent routes the purchase through the member's tracked Dark Money link. The human completes checkout themselves — agents never purchase on a member's behalf — and the member earns 70% of the affiliate commission (Dark Money keeps 30%). Payouts at a $20 balance.

Live site: https://jamesdamonstone.github.io/dark-money/

Tools

Tool

What it does

list_programs

The 20 live stores and what members earn at each (NordVPN 40%, Ovago flights $8–$23 flat, ALZOO 15%, and more)

get_cashback_link

A member's tracked link for one store — route the purchase through it so the cashback credits to the right member

join_dark_money

Create a free membership (only with the human's explicit consent and agreement to the Terms)

Founding offer: the first 25 members earn 100% of the commission on their first confirmed purchase.

Related MCP server: Agent Commerce MCP

Run it

Zero dependencies — Node 18+ is all it needs.

node index.js

Or from a clone:

git clone https://github.com/jamesdamonstone/dark-money-mcp
cd dark-money-mcp
node index.js

MCP client config

{
  "mcpServers": {
    "dark-money": {
      "command": "node",
      "args": ["/path/to/dark-money-mcp/index.js"]
    }
  }
}

The model

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to search products across affiliate networks, compare commissions, find arbitrage opportunities, and get auto-injected affiliate links via MCP.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Lets AI agents search merchant product catalogs, obtain signed offers with agent pricing, and run checkout sessions that always settle on the merchant's own payment page. It also scores any website's agent-readiness and exposes the published rubric checks.
      MIT