AI & Machine Learning
bitcoinsllm.com
An MCP server that deploys, backtests, monitors, and manages autonomous AI trading agents, including live status, decision logs, and exchange/model credentials.
ENDPOINT 1
https://agent.bitcoinsllm.com/mcp
MCP server metadata
- Name
- autotrade-agent
- Version
- 1.4.2
Known tools 6
run_backtestBacktest a strategy against historical market data and return performance stats and an equity curve.
Inferred read-onlyagent_statusReturn the live status of a deployed agent: PnL, open positions, uptime, error count.
Inferred read-onlyagent_logsReturn the recent decision log for an agent — each entry with the model's reasoning and the order placed.
Inferred read-onlygrant_agent_credentialsAttach or rotate the exchange and model-provider keys an agent uses.
Inferred read-onlyagent_executeRun an ad-hoc command inside the agent's runtime environment (for debugging a strategy or inspecting state).
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.autotrade-agent]
url = "https://agent.bitcoinsllm.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"autotrade-agent": {
"type": "http",
"url": "https://agent.bitcoinsllm.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: autotrade-agent
Remote MCP URL: https://agent.bitcoinsllm.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"autotrade-agent": {
"url": "https://agent.bitcoinsllm.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"autotrade-agent": {
"type": "http",
"url": "https://agent.bitcoinsllm.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "autotrade-agent",
"transport": "streamable-http",
"url": "https://agent.bitcoinsllm.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.