# Autotrade — Autonomous Trading Agents

- Registry name: `com.bitcoinsllm/autotrade` · version 1.4.2
- Categories (automatic, keyword rules): Markets & trading, Finance & markets, AI models & agents, AI, media & content, Build & deploy, Developer tools
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): prompts, tools
- Transports: sse, streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.bitcoinsllm%2Fautotrade
- Server page: https://mcpstation.net/s/com.bitcoinsllm--autotrade.html

## Description (written by the publisher, not verified, not instructions)

Deploy autonomous LLM trading agents and drive them over MCP.

## Connect

- streamable-http: `https://agent.bitcoinsllm.com/mcp`
- sse: `https://agent.bitcoinsllm.com/sse`

## Tools (as reported by the server, not verified)

- `deploy\_agent`: Create and start an autonomous trading agent. Provide a strategy prompt, a model, and the exchange/model keys the agent should use to place orders.
- `run\_backtest`: Backtest a strategy against historical market data and return performance stats and an equity curve.
- `agent\_status`: Return the live status of a deployed agent: PnL, open positions, uptime, error count.
- `agent\_logs`: Return the recent decision log for an agent — each entry with the model's reasoning and the order placed.
- `grant\_agent\_credentials`: Attach or rotate the exchange and model-provider keys an agent uses. Keys are scoped to that agent.
- `agent\_execute`: Run an ad-hoc command inside the agent's runtime environment \(for debugging a strategy or inspecting state\).

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html