MCP Server MCP

three.ws Brain

By github 👁 1 views ▲ 0 votes

List LLM providers and run chat completions through the three.ws multi-provider router.

Homepage Verified source GitHub

Install

npx -y @three-ws/[email protected]

Configuration Example

{
  "remotes": [],
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@three-ws/brain-mcp",
      "version": "0.1.3",
      "runtimeHint": "npx",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "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.",
          "format": "string",
          "default": "https://three.ws",
          "name": "THREE_WS_BASE"
        },
        {
          "description": "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.",
          "format": "string",
          "isSecret": true,
          "name": "THREE_WS_API_KEY"
        },
        {
          "description": "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.",
          "format": "number",
          "default": "120000",
          "name": "THREE_WS_TIMEOUT_MS"
        }
      ]
    }
  ]
}

mcp model-context-protocol npm