
Three.Ws Brain
- 89 repo stars
- Updated July 28, 2026
- nirholas/three.ws
Lists LLM providers and runs chat completions through the three.ws multi-provider router, with free open-weight tiers and paid flagships behind one key.
About
three.ws Brain is an MCP server that fronts a multi-provider LLM router: it lists available providers and runs chat completions across them, from free open-weight tiers (GPT-OSS 120B, NVIDIA NIM) to paid first-party flagships behind a single API key. A solo builder reaches for it to give an agent one switchable LLM backend instead of wiring each provider SDK separately.
- One router across many LLM providers
- Free GPT-OSS 120B + NVIDIA NIM tiers
- Paid flagships (Claude, GPT-4o, o3, Qwen, DeepSeek) via key
- Streams collapsed into a single reply
Three.Ws Brain by the numbers
- Data as of Jul 28, 2026 (Skillselion catalog sync)
claude mcp add --env THREE_WS_BASE=YOUR_THREE_WS_BASE --env THREE_WS_API_KEY=YOUR_THREE_WS_API_KEY --env THREE_WS_TIMEOUT_MS=YOUR_THREE_WS_TIMEOUT_MS brain-mcp -- npx -y @three-ws/brain-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 89 |
|---|---|
| Package | @three-ws/brain-mcp |
| Transport | STDIO |
| Auth | Required |
| Last updated | July 28, 2026 |
| Repository | nirholas/three.ws ↗ |
What it does
Lists LLM providers and runs chat completions through the three.ws multi-provider router, with free open-weight tiers and paid flagships behind one key.
Who is it for?
agents needing one switchable LLM backend
Skip if: teams needing streaming token deltas
What you get
- provider list
- chat completions