three.ws Brain

io.github.nirholas由 GitHub 帳號 nirholas 發布v0.1.4更新於 Oct 24, 2026

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

發布方自己的服務：BrainDog

已驗證STDIO僅桌面開發者工具 AI 與機器學習

服務詳細資訊

識別碼: io.github.nirholas/brain-mcp
傳輸: STDIO
執行環境: Desktop only
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 nirholas。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.nirholas%2Fbrain-mcp.svg)](https://sourceweft.com/mcp/io.github.nirholas%2Fbrain-mcp?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

本機 stdio MCP 伺服器，讓助理透過 three.ws 多供應商路由列出 LLM 供應商並執行對話補全。

可以做什麼: 列出可用的 LLM 供應商，包含識別碼、網路、等級、最大輸出、即時可用性以及是否需要金鑰
透過指定供應商執行對話補全，回傳回覆內容、實際路由、token 用量與耗時
免費開放權重模型不需金鑰，付費一線旗艦模型需 three.ws API 金鑰
所選模型短暫無法使用時，自動回退到鏡像或免費等級
適用情境: 適合希望助理透過單一端點存取多家模型廠商、而不必逐一串接各家 SDK 的情境，也方便在 Claude、GPT、o3、Grok、Qwen、DeepSeek 與開放權重模型之間比較或路由請求。
執行需求: 透過 npx 在本機執行，需要 Node.js 20 或更新版本。需能連線 three.ws，或以 THREE_WS_BASE 指定自訂位址。選用的 THREE_WS_API_KEY（Bearer 權杖）可解鎖付費旗艦模型；選用的 THREE_WS_TIMEOUT_MS 設定單次請求逾時，預設 120000 毫秒。

安裝前請注意

提示詞與訊息會送到 three.ws 路由並轉發給第三方模型供應商，請勿提交機密內容。付費旗艦模型需要 THREE_WS_API_KEY，可能在 three.ws 帳戶產生費用。工具為唯讀，不會變更平台狀態，但供應商可用性與結果每次呼叫可能不同。

安裝

在 SourceWeft 中

開啟儀表板中的 three.ws Brain，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照儲存庫中的啟動說明。

README

[three.ws]

@three-ws/brain-mcp

Any model, one interface — discover LLM providers and run chat completions through the three.ws multi-provider router, from any AI agent.

[npm] [license] [node] [MCP Registry] [three.ws]

A Model Context Protocol server that gives any AI assistant the three.ws multi-provider LLM router over stdio. Discover which models are available — Claude, the GPT-5.6 family, o3, Grok, Qwen, DeepSeek, NVIDIA Nemotron, IBM Granite, and more — and run a chat completion through whichever one fits, without wiring each vendor SDK yourself.

The router fronts every provider behind one endpoint and transparently falls back across mirrors and free tiers if the chosen model is briefly down. The free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key; the paid first-party flagships unlock with a three.ws API key.

Install

Or run with npx (no install):

Quick start

Claude Code, one line:

To unlock the paid flagships, pass your three.ws API key:

Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):

json

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

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

Inspect the surface with the MCP Inspector:

Tools

Tool	Type	What it does
`list_providers`	read-only	List every LLM the router can reach — key, network, tier, max output, live availability, and whether it needs auth.
`chat`	read-only	Run a chat completion through the chosen provider; returns the full reply, the route taken, token usage, and timing.

Both tools read live data — the provider set and completions vary between calls, so neither is idempotent. chat does not mutate any platform state, so it is annotated read-only.

Input parameters

list_providers — no parameters.

chat — messages (required: 1–100 turns of { role: "user" | "assistant", content }, content ≤ 16,000 chars), provider (provider key from list_providers, default gpt-oss-120b), system (optional system prompt, ≤ 8,000 chars), maxTokens (optional, 64–16384, default 4096, clamped to the model's ceiling).

Example

Both responses below are shape illustrations — the live provider set and generations will differ.

jsonc

// list_providers (example response)> {}{  "ok": true,  "count": 34,  "available": 33,  "default_provider": "gpt-oss-120b",  "providers": [    { "key": "gpt-oss-120b", "label": "GPT-OSS 120B", "network": "OpenAI · OpenRouter", "tier": "balanced", "maxOutput": 8192, "description": "Open-weight 120B from OpenAI. Fast, capable, free tier. Platform default.", "available": true, "requiresAuth": false },    { "key": "claude-sonnet-5", "label": "Claude Sonnet 5", "network": "Anthropic", "tier": "balanced", "maxOutput": 16384, "description": "Near-Opus quality on coding and agentic work at Sonnet cost. Best for most tasks.", "available": true, "requiresAuth": true },    { "key": "deepseek-r1", "label": "DeepSeek R1", "network": "DeepSeek", "tier": "reasoning", "maxOutput": 8192, "description": "Open reasoning model. Strong at math and code.", "available": true, "requiresAuth": true }    /* … */  ]}

// list_providers (example response)> {}{  "ok": true,  "count": 34,  "available": 33,  "default_provider": "gpt-oss-120b",  "providers": [    { "key": "gpt-oss-120b", "label": "GPT-OSS 120B", "network": "OpenAI · OpenRouter", "tier": "balanced", "maxOutput": 8192, "description": "Open-weight 120B from OpenAI. Fast, capable, free tier. Platform default.", "available": true, "requiresAuth": false },    { "key": "claude-sonnet-5", "label": "Claude Sonnet 5", "network": "Anthropic", "tier": "balanced", "maxOutput": 16384, "description": "Near-Opus quality on coding and agentic work at Sonnet cost. Best for most tasks.", "available": true, "requiresAuth": true },    { "key": "deepseek-r1", "label": "DeepSeek R1", "network": "DeepSeek", "tier": "reasoning", "maxOutput": 8192, "description": "Open reasoning model. Strong at math and code.", "available": true, "requiresAuth": true }    /* … */  ]}

jsonc

// chat (example response)> {    "provider": "claude-sonnet-5",    "system": "You are terse.",    "messages": [{ "role": "user", "content": "Name three Solana RPC methods." }]  }{  "ok": true,  "provider": "claude-sonnet-5",  "model": "Claude Sonnet 5",  "network": "Anthropic",  "tier": "balanced",  "routed_via": null,  "content": "getBalance, getAccountInfo, getSignaturesForAddress.",  "usage": { "input_tokens": 24, "output_tokens": 14, "total_tokens": 38 },  "timing_ms": { "first_token": 412, "total": 980 }}

// chat (example response)> {    "provider": "claude-sonnet-5",    "system": "You are terse.",    "messages": [{ "role": "user", "content": "Name three Solana RPC methods." }]  }{  "ok": true,  "provider": "claude-sonnet-5",  "model": "Claude Sonnet 5",  "network": "Anthropic",  "tier": "balanced",  "routed_via": null,  "content": "getBalance, getAccountInfo, getSignaturesForAddress.",  "usage": { "input_tokens": 24, "output_tokens": 14, "total_tokens": 38 },  "timing_ms": { "first_token": 412, "total": 980 }}

routed_via is null when the requested provider answered directly; otherwise it names the mirror or free-tier route the router fell back to (so you always get an answer even if the first choice is briefly down).

Model availability is dynamic. Always call list_providers first rather than hardcoding a key. The current Claude ids are claude-fable-5, claude-opus-5, claude-sonnet-5, claude-opus-4-7, claude-sonnet-4-6, and claude-haiku-4-5, but the live list is the source of truth.

Authentication

Model class	Needs a key?
Free open-weight tiers (GPT-OSS 120B, and the NVIDIA NIM set: Nemotron 3 Super / Nemotron Super 49B / Nemotron Nano / DeepSeek V4 / Kimi K2 / Llama 4 Maverick / MiniMax M2)	No
Paid first-party flagships (Claude, GPT-5.6, o3, Qwen Plus, DeepSeek, …)	Yes — set `THREE_WS_API_KEY`

Create an API key at three.ws/dashboard/developers. Without it, paid models return a sign-in error and list_providers flags them with requiresAuth: true.

Requirements

Node.js >= 20.
Network access to https://three.ws (or your own THREE_WS_BASE).

Environment variables

Variable	Required	Default	Purpose
`THREE_WS_BASE`	no	`https://three.ws`	API base URL (override to self-host or target a preview).
`THREE_WS_API_KEY`	no	—	Bearer credential that unlocks the paid first-party flagships.
`THREE_WS_TIMEOUT_MS`	no	`120000`	Per-request timeout (completions stream server-side).

Errors

A failed tool call returns an MCP error result (isError: true) whose text is a single JSON object — { "ok": false, "error": "<code>", "message": "…" }, plus status and detail on upstream rejections:

`error`	Meaning	Recovery
`upstream_error`	The router rejected the request — `status` carries the real HTTP code: `400` (bad arguments or an unknown provider key), `401` (paid model without a valid `THREE_WS_API_KEY`), `429` (rate-limited), `502` (the model's stream failed before producing output).	Act on `status`; for `401` set a key, for an unknown key re-run `list_providers`.
`timeout`	No complete response within `THREE_WS_TIMEOUT_MS`. Long flagship generations can be slow — the default 120 s matches the router's own ceiling.	Retry, lower `maxTokens`, or pick a `fast`-tier provider.
`network_error`	The request never reached the router (DNS, offline, TLS).	Check connectivity / `THREE_WS_BASE`.
`bad_config`	`THREE_WS_TIMEOUT_MS` is not a positive number (thrown at startup).	Fix the env var.

If the requested provider fails mid-flight the router transparently falls back to a mirror or free tier and the reply's routed_via names the route taken — you only see an error when every route is exhausted.