three.ws Brain MCP Server

What the code does

We read the source, 22 h ago · rules 995398eba69f

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

        await fs.writeFile(out, bytes);

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

        'http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/token',

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        const r = await redis.eval(

                return JSON.parse(await readFile(path.join(base, rel), 'utf8'));

    const child = spawn(command[0], command.slice(1), { stdio: 'inherit', shell: false });

    const drop = STANDING_HIP_HEIGHT * (root.height - 1) + root.rise;

            if (reset) { state.cursor = null; state.total = 0; grid.innerHTML = skeletons(); stateEl.hidden = true; }

        `https://api.telegram.org/bot${cfg.token}/sendMessage`,

    'UklGRmQBAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YUABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA…

    <script type="module" src="https://three.ws/agent-3d/latest/agent-3d.js"></script>

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add brain-mcp -- npx -y @three-ws/brain-mcp

{
  "mcpServers": {
    "brain-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/brain-mcp"
      ]
    }
  }
}

[mcp_servers.brain-mcp]
command = "npx"
args = ["-y", "@three-ws/brain-mcp"]

{
  "mcpServers": {
    "brain-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/brain-mcp"
      ]
    }
  }
}

{
  "servers": {
    "brain-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/brain-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: THREE_WS_BASE (Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment), THREE_WS_API_KEY (Optional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-5, o3, Grok, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/dashboard/developers), THREE_WS_TIMEOUT_MS (Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer).