MCP for AI agents

Connect your AI assistant to live Data Monetization workflows.

Use one secured, product-aware MCP server from ChatGPT, Claude, Cursor, VS Code, Codex, or your own agent runtime.

Connect the MCP server Read setup documentation

Remote MCP endpointhttps://monetize.nordicdevhouse.com/api/mcp

Streamable HTTP · OAuth 2.0

0tools3resources2prompts

Available capabilities

Data Monetization

MCP

Resources and prompts are ready

This product exposes product data and reusable prompts without callable API tools.

Connect from your client

Choose your AI client

ChatGPT

In ChatGPT developer mode, create a custom MCP connection and paste the endpoint below. OAuth starts automatically.

Copy this configuration · URL

https://monetize.nordicdevhouse.com/api/mcp

Claude / Claude Code

Add the remote HTTP server in Claude or Claude Code, then complete OAuth with /mcp.

Copy this configuration · Shell

claude mcp add --transport http data-monetization-mcp https://monetize.nordicdevhouse.com/api/mcp

Cursor

Add this server to your project or user MCP configuration.

Copy this configuration · JSON

{
  "mcpServers": {
    "data-monetization-mcp": {
      "url": "https://monetize.nordicdevhouse.com/api/mcp"
    }
  }
}

VS Code

Add this server to .vscode/mcp.json or your user MCP configuration.

Copy this configuration · JSON

{
  "servers": {
    "data-monetization-mcp": {
      "type": "http",
      "url": "https://monetize.nordicdevhouse.com/api/mcp"
    }
  }
}

Codex

Add the remote Streamable HTTP server with the Codex CLI. Codex stores the connection in your MCP configuration.

Copy this configuration · Shell

codex mcp add data-monetization-mcp --url https://monetize.nordicdevhouse.com/api/mcp

OpenAI Responses API

Use the remote MCP tool in the Responses API and keep approval enabled for non-read operations.

Copy this configuration · JSON

{
  "type": "mcp",
  "server_label": "data-monetization-mcp",
  "server_url": "https://monetize.nordicdevhouse.com/api/mcp",
  "require_approval": {
    "always": {
      "read_only": false
    },
    "never": {
      "read_only": true
    }
  }
}

Designed for controlled automation

The agent only gets the access you grant.

Read-only tools run with least-privilege scopes.

Write and destructive tools require explicit approval.

OAuth discovery and scoped authorization are built in.

Every call preserves request and trace identifiers for auditing.

Review security Read setup documentation