MCP for Agents

Use BotSpot from ChatGPT, Claude, Claude Code, Codex, Gemini CLI, Cursor, or another MCP-compatible client.

Wire contract: MCP 2026-07-28 over stateless HTTP POST. Current clients negotiate this automatically.

Create API key
Setup guides

Connect from the AI tool you already use

Every guide is visible on this page so people and AI assistants can read the complete setup without opening tabs.

OAuth connector

ChatGPT

Best for
Asking ChatGPT to inspect BotSpot strategies, broker context, backtests, and deployment state.
Authentication
OAuth
  1. Enable developer modeUse ChatGPT on the web. Open Settings -> Security and login, then enable Developer mode. Availability can depend on account and workspace policy.
  2. Add BotSpotOpen ChatGPT Plugins, select the plus button, and create a connection named BotSpot.
  3. Enter server URLChoose the public server URL connection method and paste https://mcp.botspot.trade/mcp. Keep the complete /mcp path.
  4. AuthorizeCreate the connection, complete BotSpot OAuth when prompted, then review the discovered tools and confirmation behavior.
  5. Use it in chatStart a new chat and select BotSpot from the tools menu, or refer to BotSpot in your prompt.
Server URL
https://mcp.botspot.trade/mcp
Remote MCP

Claude

Best for
Keeping Claude connected to the same BotSpot strategy and execution context you use in the app.
Authentication
OAuth
  1. Add BotSpotIndividual users open Customize -> Connectors, click + -> Add custom connector and paste the MCP host URL. Team and Enterprise owners add it first under Organization settings -> Connectors.
  2. AuthorizeComplete OAuth, then enable BotSpot for the conversation from + -> Connectors.
Server URL
https://mcp.botspot.trade
CLI setup

Claude Code

Best for
Working from a terminal while still referencing your BotSpot library, revisions, and backtest evidence.
Authentication
BotSpot API key
  1. Create a keyCreate a BotSpot API key and export it as BOTSPOT_API_KEY.
  2. Install MCPRun the command below from your shell.
Claude Code command
claude mcp add --transport http botspot https://mcp.botspot.trade/mcp --header "Authorization: Bearer $BOTSPOT_API_KEY"
CLI, desktop, and IDE setup

Codex

Best for
Researching markets and working with your BotSpot strategies, revisions, and backtest evidence from Codex.
Authentication
BotSpot API key
  1. Create a keyCreate a BotSpot API key and export it as BOTSPOT_API_KEY.
  2. Configure BotSpotAdd the configuration below to ~/.codex/config.toml or a trusted project's .codex/config.toml.
  3. Confirm the connectionOpen Codex and use /mcp, or run codex mcp list.
Codex config
[mcp_servers.botspot]
url = "https://mcp.botspot.trade/mcp"
bearer_token_env_var = "BOTSPOT_API_KEY"
CLI setup

Gemini CLI

Best for
Using Gemini CLI with the same BotSpot strategies, broker context, backtests, and trading workflows.
Authentication
OAuth
  1. Add BotSpotRun the command below to add the hosted BotSpot MCP server.
  2. AuthorizeLet Gemini CLI discover BotSpot OAuth, then complete the browser login when prompted. Use /mcp auth botspot if authentication is still required.
  3. Confirm the connectionRun gemini mcp list and check that BotSpot is connected.
Gemini CLI command
gemini mcp add --transport http botspot https://mcp.botspot.trade/mcp
IDE setup

Cursor

Best for
Bringing BotSpot strategy context into a code editor without copying credentials into prompts.
Authentication
BotSpot API key
  1. Choose scopeUse .cursor/mcp.json for one project or ~/.cursor/mcp.json globally.
  2. Add BotSpotPaste the config below and replace the placeholder with a BotSpot API key.
Cursor MCP config
{
  "mcpServers": {
    "botspot": {
      "url": "https://mcp.botspot.trade/mcp",
      "headers": {
        "Authorization": "Bearer botspot_YOUR_API_KEY"
      }
    }
  }
}