MCP Server

The Insert Affiliate MCP server gives AI assistants direct access to this documentation and to our SDK READMEs. Connect it to Claude, ChatGPT, Cursor or any other MCP client, and your assistant can look up the exact setup steps for your stack while it helps you integrate.

Server URL

https://api.insertaffiliate.com/mcp

The server uses the Streamable HTTP transport and requires no authentication.

Connecting Your Assistant

Claude Code

claude mcp add --transport http insert-affiliate https://api.insertaffiliate.com/mcp

Cursor

Add the server to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "insert-affiliate": {
      "url": "https://api.insertaffiliate.com/mcp"
    }
  }
}

Claude

  1. Open Settings → Connectors
  2. Click Add custom connector
  3. Paste the server URL and save

Other Clients

Any client that supports remote MCP servers can connect. Add a custom connector or remote server, paste the server URL, and leave authentication empty.

What Your Assistant Can Do

ToolWhat it does
search_docsSearches this documentation and returns the best matching sections
get_doc_pageReturns the full text of one documentation page
get_integration_guideReturns the ordered setup steps for your platform, purchase provider and deep linking platform
get_sdk_readmeReturns one section of an Insert Affiliate SDK README, such as the install steps or deep linking setup
troubleshootTakes a symptom and returns the matching fix from the troubleshooting guide and your SDK's README

Documentation is available in English, Spanish and Portuguese.

The server also provides an integrate_insert_affiliate prompt. In clients that support MCP prompts it appears as a command that starts a guided integration.

Example Prompts

  • "Add Insert Affiliate to my React Native app. I use RevenueCat."
  • "How do I set up Insert Links on Android?"
  • "My short codes are not attributing purchases. What should I check?"
  • "How do automatic payouts work?"

Data We Record

We record which tool was called and the text of the request, so we can see what people look for and improve the docs. We do not record who made the request.