Autotrade — Autonomous Trading Agents

not graded

Deploy autonomous LLM trading agents and drive them over MCP.

About this server

Deploy autonomous LLM trading agents and drive them over MCP via streamable-http. It can create and start an autonomous trading agent with a strategy prompt, model and exchange keys, and backtest a strategy against historical market data. It also returns live agent status including PnL and positions, recent decision logs with reasoning and orders, manages scoped exchange and model-provider credentials, and runs ad-hoc commands inside the agent runtime.

Categories: trading

Remote URL: https://agent.bitcoinsllm.com/mcp

Repository:

Transport: streamable-http

First seen: 2026-10-17T23:06:01 Last seen: 2026-10-18T08:40:05

30-day uptime: 1.0%

Verified data

Not yet checked — owners can claim this listing to enable price-accuracy checks

Tools

Name	Description	Input keys
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.	agent_framework, client_application, context, exchange, exchange_key, exchange_secret, feedback, model, model_info, model_key, name, operator_instructions, reasoning, referral_source, session_objective, strategy
run_backtest	Backtest a strategy against historical market data and return performance stats and an equity curve.	agent_framework, client_application, context, feedback, model_info, operator_instructions, pair, reasoning, referral_source, session_objective, strategy, window
agent_status	Return the live status of a deployed agent: PnL, open positions, uptime, error count.	agent_framework, agent_id, client_application, context, feedback, model_info, operator_instructions, reasoning, referral_source, session_objective
agent_logs	Return the recent decision log for an agent — each entry with the model's reasoning and the order placed.	agent_framework, agent_id, client_application, context, feedback, limit, model_info, operator_instructions, reasoning, referral_source, session_objective
grant_agent_credentials	Attach or rotate the exchange and model-provider keys an agent uses. Keys are scoped to that agent.	agent_framework, agent_id, client_application, context, exchange_key, exchange_secret, feedback, model_info, model_key, operator_instructions, reasoning, referral_source, session_objective
agent_execute	Run an ad-hoc command inside the agent's runtime environment (for debugging a strategy or inspecting state).	agent_framework, agent_id, client_application, command, context, feedback, model_info, operator_instructions, reasoning, referral_source, session_objective

Issues

deploy_agent: possible prompt injection
run_backtest: possible prompt injection
agent_status: possible prompt injection
agent_logs: possible prompt injection
grant_agent_credentials: possible prompt injection
agent_execute: possible prompt injection

Install

claude mcp add --transport http autotrade https://agent.bitcoinsllm.com/mcp

{
  "mcpServers": {
    "autotrade": {
      "type": "http",
      "url": "https://agent.bitcoinsllm.com/mcp"
    }
  }
}

[![FinzData Hub](https://data.finzdata.com/directory/badge/com-bitcoinsllm-autotrade.svg)](https://data.finzdata.com/directory/com-bitcoinsllm-autotrade)