Trade Agent MCP Server

by PortFray

370 downloads
Not rated
GitHub

About

Guide to connect to Trade Agent's MCP server and trade stocks and crypto

Details

Author
PortFray
Downloads
370
Categories
AI

- Natural language trade execution (e.g., "Buy $500 of Apple")
- Secure brokerage integration (Robinhood, E*TRADE, Coinbase, Kraken)
- Portfolio queries (coming soon)
- Market queries (coming soon)
- Remote-only; no local deployment required

Create an account at thetradeagent.ai, sign up for the Pro plan’s free trial, and connect your brokerage. Then point your MCP-compatible agent platform to the endpoint https://mcp.thetradeagent.ai/sse and authenticate via the browser-based OAuth flow.

Trade Agent MCP Server

Endpoint: https://mcp.thetradeagent.ai/sse
Mode: Remote-only (no local deployment required)

Overview

The Trade Agent MCP Server provides a conversational trading interface for agents. It enables natural-language interaction with stock and crypto brokerages—agents can execute trades, query portfolio performance, and surface market insights by sending plain-English requests through the MCP protocol.

This server is remote-only—you don't need to run anything locally to connect. Just point your MCP-compatible agent platform to the URL above.

---

Features

- 💬 Natural Language Trade Execution
Example: "Buy $500 of Apple" or "Sell 10 shares of SPY"

- 🔐 Secure Brokerage Integration
Supports Robinhood, E*TRADE, Coinbase, and Kraken. More to be added soon!

- 📊 COMING SOON: Portfolio Queries
Example: "How is my portfolio doing?" or "What’s my exposure to tech?"

- 🔍 COMING SOON: Market Queries
Example: "How is Berkshire performing relative to the S&P?"

---

Getting Started

1. First, create an account at https://thetradeagent.ai.
2. Sign up for the Pro plan's free trial.
3. Connect your brokerage of choice.

Connecting

1. Connect your MCP client to https://mcp.thetradeagent.ai/sse. 2. Authenticate through the browser-based OAuth flow. 3. You're now ready to start trading!
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.