AAI Gateway

io.github.gybob由 GitHub 帳號 gybob 發布v1.1.10更新於 Oct 24, 2026

Unified MCP & Skill management gateway, shared across AI agents, 99% context token savings

概覽

AI 產生的概覽

本機閘道,把 MCP 伺服器與技能包統一註冊為「Agent App」,讓助理依需求搜尋、安裝、啟用並呼叫它們。

可以做什麼
  • 用自然語言搜尋並安裝新的工具或 Agent App
  • 把 MCP 伺服器與技能包匯入為受管理的 Agent App
  • 列出已註冊的 Agent App,並依助理啟用或停用
  • 移除 Agent App,並執行其中某個特定工具
  • 把每個匯入的應用程式暴露為 app_ 工具,呼叫時回傳操作指南與工具清單
  • 在本機已安裝時自動探索 Claude Code、Codex、OpenCode 等預設應用程式
適用情境
適合同時讓多個 AI 助理接入大量 MCP 伺服器或技能、希望以一份共用註冊表取代逐一助理重複設定的情境,也適合希望工具描述按需載入、而非每輪對話都注入的情況。
執行需求
以本機 stdio 程序在使用者電腦上執行,透過 npx 從 npm 套件 aai-gateway 啟動,需要 Node.js 以及下載套件的網路存取。未宣告驗證、環境變數或標頭。僅限桌面環境,不提供網頁版。
安裝前請注意
此閘道可安裝並匯入第三方 MCP 伺服器與技能包,並執行其中的工具,因此會在你的電腦上執行來自外部的程式碼與工具。它也能移除 Agent App,並改變各助理啟用的應用程式。依賴前請先確認將要安裝的內容。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AAI Gateway,將其新增到工作區。
  2. 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

English | 简体中文 | 日本語 | 한국어


AAI Gateway: Unified MCP & Skill Management, Shared Across AI Agents, 99% Context Token Savings

[npm version] [license]


What Is It

AAI = Agent App Interface

AAI Gateway is the interaction gateway for Agent Apps.

What is an Agent App? An Agent App is a collection of capabilities that an Agent can use. For example:

  • An MCP Server is an Agent App — it provides a set of tools
  • A Skill package is an Agent App — it provides one or more skills

In AAI Gateway, they are abstracted as Agent Apps under unified management. Import once, and all AI Agents can use them immediately.


What Problems Does It Solve

Context Bloat

Traditional: 10 MCPs × 5 tools = 50 full schemas ≈ 7,500 tokens injected into every conversation.

AAI Gateway: each Agent App needs only fewer than 50 tokens for a summary, with details loaded on demand. 99% token savings.

Finding Tools Is Hard

Traditional: search GitHub → read READMEs → copy JSON configs → debug connections → restart Agent.

AAI Gateway: tell your Agent "use AAI to search for xxx" — auto-searches, installs, ready to use.

"Use AAI to search for a browser automation tool"

→ Search → finds Playwright MCP → Agent summarizes a one-line Agent App summary → install → ready to use, no restart needed

"Use AAI to search for a PPT creation skill"

→ Search → finds PPT Skill → uses skill description as Agent App summary → install → ready to use, no restart needed

Duplicate Config

Configure the same thing in Claude Code, Codex, and OpenCode separately? Import once through AAI Gateway, all Agents share instantly.


Quick Start (30 Seconds)

Claude Code:

bash
claude mcp add --scope user --transport stdio aai-gateway -- npx -y aai-gateway

Codex:

bash
codex mcp add aai-gateway -- npx -y aai-gateway

OpenCode — add to ~/.config/opencode/opencode.json:

json
{  "mcp": {    "aai-gateway": {      "type": "local",      "command": ["npx", "-y", "aai-gateway"],      "enabled": true    }  }}

OpenClaw:

bash
openclaw plugins install openclaw-aai-gateway-plugin

Once installed, just tell your Agent what you want to do.


Built-in Tools

ToolDescription
search:discoverSearch and install new tools with natural language
mcp:importImport an MCP Server as an Agent App
skill:importImport a Skill package as an Agent App
listAllAaiAppsList all registered Agent Apps
enableApp / disableAppEnable or disable an Agent App per Agent
removeAppRemove an Agent App
aai:execExecute a specific tool within an Agent App

Each imported Agent App generates an app_<app-id> tool that returns the full operation guide and tool list when called.

Preset Agent Apps (auto-discovered when locally installed)

App IDNameDescription
claudeClaude CodeAI coding assistant for code editing, analysis, and development
codexCodexOpenAI-powered AI coding assistant
opencodeOpenCodeAI development assistant for editing files and running commands

Architecture

[Architecture]


Developers: Get Your Agent App Auto-Discovered

Create an aai.json descriptor and submit it to src/discovery/descriptors/. When a user's local environment meets the discovery.checks conditions, the Agent will auto-discover your Agent App.

json
{  "schemaVersion": "2.0",  "version": "1.0.0",  "app": {    "name": { "default": "My App" }  },  "discovery": {    "checks": [      { "kind": "command", "command": "my-app" }    ]  },  "access": {    "protocol": "mcp",    "config": {      "command": "my-app-mcp",      "args": ["--stdio"]    }  },  "exposure": {    "summary": "Use when the user wants to do X."  }}

discovery.checks supports three check types: command (command exists), file (file exists), path (directory exists).

Supported protocols: mcp, skill, acp-agent

Welcome to submit a PR to contribute new Agent App descriptors, or open an issue for feedback.

來源:README.md,提交 8ef730b

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v1.1.10最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分