io.github.nirholas/brain-mcp icon
io.github.nirholas

brain-mcp

three.ws Brain

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

stdiocommunityservice

Package Details

@three-ws/brain-mcp

0.1.0•https://www.npmjs.com/package/@three-ws/brain-mcp
Transportstdio
Runtimenpx

Environment Variables

THREE_WS_BASE(str)
Default:https://three.ws

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(str)
Secret

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-4o, o3, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/account.

THREE_WS_TIMEOUT_MS(num)
Default:120000

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.