# Tradetron MCP server > Build, backtest and diagnose algo trading strategies in your own Tradetron account by describing them in plain English. - Listing: https://mcp.tc/i/tradetron - Connect: use the server's own URL `https://mcp.tradetron.tech/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [Finance & Payments](https://mcp.tc/c/finance-payments) - Vendor: Tradetron - Homepage: ## About Connects an AI assistant to your Tradetron account so you can build algo trading strategies, run backtests, change individual legs and find out why a deployed strategy did or didn't trade. Keywords are looked up and fields validated before a strategy is saved. The connector never places an order. Runs as a hosted streamable HTTP endpoint at https://mcp.tradetron.tech/mcp. Users sign in with their Tradetron account in the browser, and every tool works only on that account. Connecting is free. ## What it can do - Build trading strategies from a plain-English description - Backtest from chat and get the full report link - Sweep a parameter or compare two strategy versions - Change one leg of a strategy without rebuilding it - Diagnose why a deployed strategy did or didn't trade - Read engine and broker logs for your own account ## Example prompts - "Build a NIFTY weekly short straddle that exits at 30% profit" - "Backtest it from January 2022" - "Try stop losses of 20, 30 and 40% and compare the results" - "Why didn't my straddle trade this morning?" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http tradetron https://mcp.tradetron.tech/mcp ``` 2. Start Claude Code, type `/mcp`, pick **tradetron** and choose **Authenticate**. A browser window opens for the Tradetron sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**. 2. Name it **Tradetron** and paste this URL: ```url https://mcp.tradetron.tech/mcp ``` 3. Click **Add**, then **Connect**, and sign in when Tradetron asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://mcp.tradetron.tech/mcp` and click **Add**. 3. Click **Connect** and sign in when Tradetron asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**. 2. Enter a name for the server. 3. Under **Connection**, paste `https://mcp.tradetron.tech/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Tradetron to sign in. 4. Check **I understand and want to continue**, then select **Create as a plugin**. Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can). ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "tradetron": { "url": "https://mcp.tradetron.tech/mcp" } } } ``` Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"tradetron","type":"http","url":"https://mcp.tradetron.tech/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "tradetron": { "type": "http", "url": "https://mcp.tradetron.tech/mcp" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "tradetron": { "serverUrl": "https://mcp.tradetron.tech/mcp" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add tradetron --url https://mcp.tradetron.tech/mcp codex mcp login tradetron ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.tradetron] url = "https://mcp.tradetron.tech/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http tradetron https://mcp.tradetron.tech/mcp ``` Then, inside Gemini CLI, run `/mcp auth tradetron` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "tradetron": { "type": "http", "url": "https://mcp.tradetron.tech/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.tradetron.tech/mcp`. ## Details - Server version: 0.4.1 - Last checked: 2026-11-15 (reachable, asks for credentials) - Listed: 2026-10-24 - Updated: 2026-10-24 --- Source: https://mcp.tc/i/tradetron (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report