Skip to content
Autotrade logo

Autotrade MCP server

Which MCP servers are Autotrade's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to Autotrade

Whose server it is
  • Registry namecom.bitcoinsllm/autotradeverified in the MCP registry

The registry name sits under bitcoinsllm.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools6
  • Server calls itselfautotrade-agent
  • Server version1.4.2
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 232 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: deploy an LLM trading agent from a strategy prompt; backtest a trading strategy on a chosen pair; check agent status and read its decision logs.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • For "deploy an LLM trading agent from a strategy prompt", the likely first call is deploy_agent.
  • For "backtest a trading strategy on a chosen pair", the likely first call is run_backtest.
  • For "check agent status and read its decision logs", the likely first call is agent_status.
  • Parameters are untyped or undescribed in 6 of 6 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 4, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer247 ms
  • Space in an agent's context≈ 4,615 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsC · 67 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 6
  • Not saying whether it only reads or can destroy: 6 of 6

What an agent can do with it

  • can do · deploy an LLM trading agent from a strategy prompt
  • can do · backtest a trading strategy on a chosen pair
  • can do · check agent status and read its decision logs

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-24
  • 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).

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://agent.bitcoinsllm.com/mcp as a custom connector in the settings.

OpenAPI spec

7 paths, read 2026-10-24. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.