Autotrade — Autonomous Trading Agents

com.bitcoinsllmPublished by bitcoinsllm.comOfficial publisherv1.4.2Updated Oct 24, 2026

Deploy autonomous LLM trading agents and drive them over MCP.

VerifiedStreamable HTTPWeb executableFinance

Overview

AI-generated overview

Lets an assistant deploy autonomous trading agents, backtest strategies, and check agent PnL, positions and decision logs.

What you can do
The server lets an assistant deploy and start autonomous trading agents that act on a strategy prompt and a chosen model. It can backtest a strategy against historical market data and return performance statistics and an equity curve, report an agent's live PnL, open positions, uptime and error count, and return the agent's decision log with reasoning and orders. It also attaches or rotates the exchange and model-provider keys an agent uses, and runs ad-hoc commands in the agent's runtime.
When to use it
Use it when you want an assistant to deploy and monitor automated trading agents, or to backtest a strategy on historical data before committing. It is not needed for plain market lookups or general financial analysis.
Requirements
A remote endpoint; no local package is needed. Using it requires exchange and model-provider API keys, a strategy prompt and a model choice.
Before you install
Agents place real orders with the supplied keys, so trading can lose money. grant_agent_credentials accepts and binds exchange and model-provider keys, and agent_execute runs arbitrary commands in the agent runtime. Deploy and backtest send strategy content to a third-party service. Check key scope and spending limits first.

Installation

In SourceWeft

  1. Open Autotrade — Autonomous Trading Agents in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.bitcoinsllm%2Fautotrade/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

6

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.

Parametersnamerequiredmodelcontextexchangefeedbackstrategyrequiredmodel_keyreasoningmodel_infoexchange_keyagent_frameworkexchange_secret+4 more

run_backtest

Backtest a strategy against historical market data and return performance stats and an equity curve.

Parameterspairwindowcontextfeedbackstrategyrequiredreasoningmodel_infoagent_frameworkreferral_sourcesession_objectiveclient_applicationoperator_instructions

agent_status

Return the live status of a deployed agent: PnL, open positions, uptime, error count.

Parameterscontextagent_idrequiredfeedbackreasoningmodel_infoagent_frameworkreferral_sourcesession_objectiveclient_applicationoperator_instructions

agent_logs

Return the recent decision log for an agent — each entry with the model's reasoning and the order placed.

Parameterslimitcontextagent_idrequiredfeedbackreasoningmodel_infoagent_frameworkreferral_sourcesession_objectiveclient_applicationoperator_instructions

grant_agent_credentials

Attach or rotate the exchange and model-provider keys an agent uses. Keys are scoped to that agent.

Parameterscontextagent_idrequiredfeedbackmodel_keyreasoningmodel_infoexchange_keyagent_frameworkexchange_secretreferral_sourcesession_objectiveclient_application+1 more

agent_execute

Run an ad-hoc command inside the agent's runtime environment (for debugging a strategy or inspecting state).

Parameterscommandrequiredcontextagent_idfeedbackreasoningmodel_infoagent_frameworkreferral_sourcesession_objectiveclient_applicationoperator_instructions

Version history

1
  1. v1.4.2LatestSep 17, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.