How to use the eToro MCP server with Cursor, Claude, and other AI code editors to build trading apps without writing API calls by hand.
You don't need to dig through scattered notes to wire up the eToro API. With the eToro Public API MCP (Model Context Protocol) server, your AI editor can discover routes, read the live OpenAPI schema, and execute calls against the real API—while you stay in your project.
This is vibe coding for fintech.
The Model Context Protocol is an open standard that lets AI assistants (like Claude in Cursor, Antigravity, or VS Code) call external tools. Instead of pasting guesses into your codebase, you describe what you want to build, and the assistant pulls structured answers from connected servers.
The eToro Public API MCP server gives your AI assistant two tools — get-all-routes and get-route-spec — that expose the full live OpenAPI document, required scopes, and request/response schemas. Your assistant queries them at inference time to write accurate API code instead of guessing.
The fastest way is to let the skill do the wiring for you. Send this prompt to your agent (Cursor, Claude Code, Antigravity, or any other MCP-capable client):
Please install the skill at https://mcp.public-api.etoro.com/skill and follow the instructions.
The skill at mcp.public-api.etoro.com/skill walks your agent through MCP registration for your specific client, authentication, demo vs real accounts, and the safety rules for money-moving routes.
The eToro Public API MCP server is hosted — no npx package, streamable HTTP transport. If you'd rather wire it up yourself, add this to your editor’s MCP config (e.g. Cursor: .cursor/mcp.json):
{
"mcpServers": {
"etoro-public-api": {
"url": "https://mcp.public-api.etoro.com"
}
}
}
Use api-portal.etoro.com to register your app and get API keys when you call the REST API directly. The MCP server uses your x-user-key to scope what your agent can do.
Open your editor and start asking. The assistant can search and read the official API portal documentation through the MCP connection so answers match what the portal publishes.
Ask your assistant to find the right Market Data or instrument endpoints, query parameters, and response shapes in the docs, then sketch the HTTP calls or client code. You still run requests against the real API with your own keys; the MCP layer helps the assistant stay aligned with documented behavior instead of inventing endpoints.
Describe the UI and data you need—for example a React view with P&L, allocation, and a sortable positions table. The assistant can look up portfolio-related endpoints, required headers, and pagination from the documentation, then generate components and types that match those contracts.
Ask the assistant to read the Trading API documentation for order payloads, demo vs. real accounts, and authentication before you implement. That cuts down on mismatches between sample code and the live API.
| Editor | MCP Support | Status |
|---|---|---|
| Cursor | Native | Fully supported |
| Claude Desktop | Native | Fully supported |
| VS Code + Continue | Plugin | Supported |
| Antigravity | Native | Supported |
| Zed | Plugin | Beta |
The future of fintech development is conversational. Start vibing with eToro today.
Was this helpful?
Use the eToro Rankings API to filter investors, fetch period-scoped performance, and build a cache-friendly leaderboard.
Walk through the social and user data endpoints to build a simple trader leaderboard using the eToro API.
Be the first to know when we publish new API guides, product updates, and builder resources.
Newsletter coming soon. We'll only email you when it launches.