MCP Server

AI-native integration with the Dual tokenization platform via the Model Context Protocol, 80 tools across 14 API modules.

AI-native integration with the Dual tokenization platform via the Model Context Protocol. The Dual MCP server is hosted, so you can connect an MCP client directly to the live endpoint without cloning or running a local server.

Quick Start

Point your MCP client at:

text
https://mcp-testnet.dual.network/mcp

Then authenticate with an API key via the X-API-Key header.

Full setup guide →

Claude Desktop Configuration

Add this to claude_desktop_config.json:

json
{
"mcpServers": {
"dual": {
"url": "https://mcp-testnet.dual.network/mcp",
"headers": {
"X-API-Key": "your-api-key"
}
}
}
}

What is MCP?

The Model Context Protocol is an open standard that lets AI systems interact with external tools through structured, typed interfaces. Instead of brittle wrappers or screen-scraping, MCP makes the agent a first-class user of the platform.

With Dual's MCP server, an AI agent can create templates, mint tokens, manage organizations, configure webhooks, inspect sequencer state, and work across the same core API modules used by the platform itself.

Example: Natural Language to Token Deployment

Note:

"Create a redeemable reward token for my brand with 1 million supply, set up a rule that expires after 12 months, and mint it on Base."

The agent can translate that request into:

  1. dual_create_template to define the token structure
  2. dual_create_action_type to register lifecycle actions
  3. dual_execute_action to mint the initial supply
  4. dual_create_webhook to monitor downstream events

API Modules

Next Steps