- Home
- MCP servers
- Divvi
Divvi
- typescript
0
GitHub Stars
typescript
Language
6 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"divvi-xyz-divvi-mcp-server": {
"command": "npx",
"args": [
"-y",
"@divvi/mcp-server"
]
}
}
}This MCP server lets AI assistants automatically integrate the Divvi referral toolkit into JavaScript and TypeScript blockchain apps. It guides the agent, analyzes your project, and applies best‑practice wiring so referral tracking works without manual boilerplate, across frontend, backend, and full‑stack setups.
How to use
Ask your AI assistant to perform a Divvi integration with simple prompts like “Integrate this dapp with Divvi” for a guided setup, or provide precise parameters to tailor the integration to your project.
When you want more control, supply the consumer address directly in the prompt, for example: “Integrate my dapp with Divvi using consumer address 0x1234…” The assistant will read the latest official Divvi SDK guidance, analyze your project structure, install the SDK if needed, and modify blockchain transactions to include referral tracking. It will also ensure referral submission after transactions and handle errors gracefully.
The integration requires your Divvi consumer address to register your dapp as a builder on Divvi. You can start with a simple prompt and then provide the exact address when prompted by the assistant.
How to install
Prerequisites you need before starting the integration:
-
Node.js 22+
-
An MCP-compatible AI assistant (for example Claude Desktop, Cursor, or Copilot)
Choose one of the quick setup methods to run the Divvi MCP server in your environment.
{
"mcpServers": {
"divvi-mcp": {
"command": "npx",
"args": ["-y", "@divvi/mcp-server"],
"env": {}
}
}
}
Additional setup notes
Client configuration is designed to be straightforward. In the simplest flow, you run the MCP server client once and then prompt your AI assistant to perform the integration. If you prefer a local development flow, you can run the server in development mode and point your assistant to the local build.
Cursor users can add the server to their settings as shown in the example below, and other MCP clients can follow the same pattern using the same command and arguments.
{
"mcpServers": {
"divvi-mcp": {
"command": "npx",
"args": ["-y", "@divvi/mcp-server"]
}
}
}
Available tools
integrate_divvi_referral_sdk
Tool that guides AI agents to integrate the @divvi/referral-sdk into a project by reading the latest SDK docs, analyzing the target project, applying integration steps, and validating the result.