MetaMesh-UGA

dev.metamesh-uga由 metamesh-uga.dev 發布官方發布者v2.0.3更新於 Nov 2, 2026

Serverless edge control plane to discover, route and monetize 14,982+ MCP tools.

已驗證Streamable HTTP可網頁執行金融開發者工具商業與電商

概覽

AI 產生的概覽

遠端閘道，讓助理搜尋 13,000+ 個 MCP 工具目錄，並透過內建 Stripe 工具讀寫 Stripe 帳戶資料。

可以做什麼
  • 搜尋並檢視 MCP 工具目錄：關鍵字檢索、含信任評分與來源的工具詳情，以及閘道概況、健康狀態、探索狀態與使用指標
  • 規劃與查詢 Stripe 整合：整合方案、文件檢索、API 操作搜尋與參數詳情
  • 透過任意 GET 操作讀取 Stripe 帳戶資料並檢視帳戶資訊
  • 透過任意 POST、PATCH、PUT 或 DELETE 操作寫入 Stripe 資料
  • 分析 Stripe Sigma 與 Metrics 資料，例如營收、扣款、發票與訂閱
  • 向 Stripe 提交產品意見回饋
適用情境
適合讓助理從大型索引目錄中尋找與比較 MCP 伺服器，或需要在同一端點取得 Stripe 整合指引並直接呼叫 Stripe API 的情境。
執行需求
遠端 streamable HTTP 端點；MCP 端點未宣告需要身分驗證。Stripe 工具作用於已登入的 Stripe 帳戶。README 中的自架方式需要 Node.js 18+、Go 1.21+、Cloudflare 帳戶與 Stripe 憑證。
安裝前請注意
Stripe 寫入工具可在真實 Stripe 帳戶中建立、修改與刪除資料，讀取與分析工具會暴露帳戶、付款與客戶資料。README 說明 REST 呼叫端點依請求透過 Stripe 或 x402 USDC 計費，而 MCP 端點據稱對探索與 metamesh 工具免費。透過 Stripe 意見回饋工具提交的內容會傳送給 Stripe。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 MetaMesh-UGA，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。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/dev.metamesh-uga%2Fmetamesh-uga/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "metamesh-uga": {
      "type": "http",
      "url": "https://api.metamesh-uga.dev/mcp"
    }
  }
}

README

MetaMesh-UGA

The MCP Operating System — A Serverless Control Plane for AI Agents and MCP Infrastructure

[MCP Registry] [Status] [MCP OS]

Set & Forget | Zero Infrastructure | Serverless | Edge Native | MCP Operating System

Live Status

  • Gateway: https://api.metamesh-uga.dev — operational
  • Dashboard: https://dashboard.metamesh-uga.dev
  • MCP endpoint: https://api.metamesh-uga.dev/mcp (JSON-RPC over HTTP)
  • MCP Registry: dev.metamesh-uga/metamesh-uga v2.0.0 — published & latest
  • Tools indexed: 13,000+ MCP servers, synced every 6h from the official MCP registry
  • Stripe billing: LIVE — agents top up a USD balance and are charged per call
  • x402 payments: implemented; activation gated by wallet config (see /v1/x402/info)

MetaMesh-UGA is the MCP Operating System: a serverless, edge-native control plane that discovers, verifies, scores, routes, monitors and scales MCP servers behind a single endpoint.

It combines registry sync, semantic discovery, trust scoring, policy enforcement, security scanning, lifecycle management, smart routing, multi-level caching, reliability patterns, self-healing and real-time analytics to make MCP infrastructure production-ready for AI agents.

Connect in seconds: point any MCP client (Claude, Windsurf, Cursor, Antigravity) at https://api.metamesh-uga.dev/mcp, or register an agent for a programmatic API key. Either way you gain access to a curated, trusted, and benchmarked catalog of MCP servers.

🚀 Caratteristiche

  • MCP Operating System: Control Plane + Data Plane per gestire l'intero ecosistema MCP
  • Unified Registry: Single source of truth con federation, mirroring e snapshot
  • Smart Discovery: Keyword, semantic search, capability graph e intent-based discovery
  • Trust Engine: Reputation score basato su uptime, latenza, success rate e security
  • Smart Routing: Weighted, latency, geographic, cost e health-based routing
  • Reliability Layer: Circuit breaker, retry, bulkhead, hedging e fallback
  • Multi-level Cache: In-memory L1 + KV L2, TTL, pattern invalidation
  • Security Fabric: Dependency scan, CVE detection, policy engine OPA/Rego
  • Self-Healing: Auto-deprecated, rollback recovery, health-based remediation
  • Analytics: Usage trends, cost analysis, performance metrics, export OTel/Prometheus
  • Lifecycle Management: Stati automatici dalla discovery all'archiviazione
  • Serverless: Zero infrastruttura da gestire (Cloudflare Workers)
  • WASM Runtime: Esecuzione sicura dei tool MCP compilati in WebAssembly
  • AI Agent Economy: Supporto nativo per x402 Protocol (micropagamenti USDC)
  • Monetizzazione: Piani Free, Pro ($19/mese), Enterprise ($499/mese)
  • Set & Forget: Automazione completa con cron triggers

📋 Requisiti

  • Node.js 18+
  • Go 1.21+ (per CLI)
  • Account Cloudflare (free tier sufficiente)
  • Account Stripe (per pagamenti)

🛠️ Installazione

1. Clone e Setup

bash
git clone https://github.com/SiouxTXT/metamesh-uga.gitcd metamesh-uganpm install

2. Configurazione Cloudflare

bash
# Installa Wranglernpm install -g wrangler
# Login a Cloudflarewrangler login
# Crea database D1wrangler d1 create metamesh-catalog
# Crea KV namespacewrangler kv:namespace create "CACHE"
# Crea R2 bucketwrangler r2 bucket create metamesh-wasm

3. Configura Secrets

bash
# Stripewrangler secret put STRIPE_SECRET_KEYwrangler secret put STRIPE_WEBHOOK_SECRET
# JWTwrangler secret put JWT_SECRET
# Alerting (opzionale)wrangler secret put TELEGRAM_BOT_TOKENwrangler secret put TELEGRAM_CHAT_ID
# Adminwrangler secret put ADMIN_KEY

4. Database Migration

bash
wrangler d1 execute metamesh-catalog --file=./shared/migrations/001_init.sql

5. Deploy

bash
# Deploy Workersnpm run deploy:workers
# Deploy Dashboardcd packages/dashboardnpm installnpm run deploy

6. Installa CLI

bash
cd cligo build -o metamesh
# Installa globalmentemv metamesh /usr/local/bin/
# O usa direttamente./metamesh connect

🎯 Uso

CLI Tool

bash
# Connetti al gateway (salva la config locale)metamesh connect
# Chiama un tool (raggiunge POST /v1/call)metamesh call example.echo --message "hello"
# Lista tool disponibilimetamesh list --category demo
# Visualizza utilizzometamesh usage

API REST

bash
# List tools (paginated, public)curl "https://api.metamesh-uga.dev/v1/tools?limit=20&sort=popularity"
# Full-text searchcurl "https://api.metamesh-uga.dev/v1/search?q=github"
# Execute a toolcurl -X POST \  -H "Content-Type: application/json" \  -d '{"tool": "example.echo", "params": {"message": "hello"}}' \  https://api.metamesh-uga.dev/v1/call

MCP Protocol

Add to Devin / Cursor / Windsurf / Claude Desktop:

json
{  "mcpServers": {    "metamesh-uga": {      "url": "https://api.metamesh-uga.dev/mcp",      "transport": "http"    }  }}

Or test directly via JSON-RPC:

bash
curl -X POST https://api.metamesh-uga.dev/mcp \  -H "Content-Type: application/json" \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

🤖 AI Agent Economy

Two complementary, production-ready payment models:

Model A — Stripe prepaid credit (recommended)

Agents top up a USD balance once via Stripe Checkout, then per-call pricing is debited automatically from the balance. No per-call fees, no crypto required.

bash
# 1. Register an agent (returns agent_id + api_key, shown once)curl -X POST https://api.metamesh-uga.dev/v1/agent/register \  -H "Content-Type: application/json" -d '{"name":"My Agent"}'
# 2. Top up via Stripe (returns a Checkout URL)curl -X POST https://api.metamesh-uga.dev/v1/agent/topup \  -H "X-Agent-Id: agent_xxx" -H "X-Agent-Key: ak_xxx" \  -H "Content-Type: application/json" -d '{"amount_usd": 10}'
# 3. Call tools — balance is debited per callcurl -X POST https://api.metamesh-uga.dev/v1/call \  -H "X-Agent-Id: agent_xxx" -H "X-Agent-Key: ak_xxx" \  -H "Content-Type: application/json" \  -d '{"tool":"example.echo","params":{"message":"hi"}}'
# 4. Check balance / historycurl https://api.metamesh-uga.dev/v1/agent/wallet -H "X-Agent-Id: agent_xxx" -H "X-Agent-Key: ak_xxx"curl https://api.metamesh-uga.dev/v1/billing/info

Operator activation:

bash
wrangler secret put STRIPE_SECRET_KEY --env production       # sk_live_... or sk_test_...wrangler secret put STRIPE_WEBHOOK_SECRET --env production   # whsec_... (Stripe webhook signing secret)# Point a Stripe webhook to: https://api.metamesh-uga.dev/v1/stripe/webhook (event: checkout.session.completed)# Optionally set BILLING_ENABLED="true" in wrangler.toml to require payment for ALL callers.

When Stripe is unset, anonymous calls stay free and /v1/agent/topup returns a clear 503.

Current production state: Stripe (live keys) and the checkout.session.completed webhook are configured, and BILLING_ENABLED="true". Enforcement applies to the REST POST /v1/call endpoint — every caller is charged per request, so top up via /v1/agent/topup first. The public MCP endpoint (POST /mcp) stays free for discovery (tools/list) and native metamesh.* tools, so MCP clients keep working without an account.

Model B — x402 crypto (USDC on Base)

The x402 protocol: agents pay per call in USDC on-chain. Send an X-PAYMENT header; on HTTP 402 read the accepts requirements.

bash
curl https://api.metamesh-uga.dev/v1/x402/info

Payment flow

  1. Call a paid resource (POST /v1/call). When enforcement is active and no payment is attached, the gateway responds HTTP 402 with a standard accepts requirements body (scheme exact, network base, asset USDC, payTo, maxAmountRequired).
  2. The agent constructs a signed payment and retries with an X-PAYMENT header (base64 JSON).
  3. The gateway verifies + settles via the configured facilitator, then returns the result plus an X-PAYMENT-RESPONSE header with the on-chain tx.

Activation (operator)

x402 is implemented but disabled until you set a receiving wallet:

bash
# In wrangler.toml [env.production.vars]X402_ENABLED = "true"X402_PAY_TO  = "0xYourBaseWallet"# X402_FACILITATOR_URL and USDC_CONTRACT have working defaults

Per-tool pricing lives in the tool_pricing table (default $0.001/call, bulk $0.0005).

📊 Architettura

MetaMesh-UGA adotta un'architettura a due piani ispirata ai service mesh moderni.

┌─────────────────────────────────────────────────────────────────────────────┐│                      META MESH-UGA — MCP OPERATING SYSTEM                 │├─────────────────────────────────────────────────────────────────────────────┤│                                                                             ││  ┌─────────────────────────────────────────────────────────────────────┐   ││  │                     CONTROL PLANE                                   │   ││  │                                                                     │   ││  │  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │   ││  │  │ Registry │ │ Discovery│ │  Trust   │ │  Policy  │ │ Lifecycle│ │   ││  │  │  Engine  │ │  Engine  │ │  Engine  │ │  Engine  │ │  Manager │ │   ││  │  └──────────┘ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │   ││  │  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐             │   ││  │  │ Security │ │Benchmark │ │Analytics │ │  Config  │             │   ││  │  │  Scanner │ │  Engine  │ │  Engine  │ │  Engine  │             │   ││  │  └──────────┘ └──────────┘ └──────────┘ └──────────┘             │   ││  └─────────────────────────────────────────────────────────────────────┘   ││                                    │                                        ││                                    ▼                                        ││  ┌─────────────────────────────────────────────────────────────────────┐   ││  │                       DATA PLANE                                    │   ││  │                                                                     │   ││  │  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │   ││  │  │  Routing │ │   Cache  │ │  Health  │ │  Proxy   │ │  Rate    │ │   ││  │  │  Engine  │ │  Engine  │ │  Engine  │ │  Engine  │ │ Limiting │ │   ││  │  └──────────┘ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │   ││  └─────────────────────────────────────────────────────────────────────┘   ││                                    │                                        ││                                    ▼                                        ││  ┌─────────────────────────────────────────────────────────────────────┐   ││  │                         MCP ECOSYSTEM                               │   ││  │  (Server MCP A, B, C, D, E...)                                     │   ││  └─────────────────────────────────────────────────────────────────────┘   │└─────────────────────────────────────────────────────────────────────────────┘
  • Control Plane: decisioni, configurazione, orchestrazione, analytics.
  • Data Plane: esecuzione delle richieste, routing, caching, health in tempo reale.

Per maggiori dettagli: docs/ARCHITECTURE.md.

💰 Piani di Pagamento

PianoPrezzoFeature
Free€01.000 chiamate/mese, 100 req/min
Pro$19/meseChiamate illimitate, 1.000 req/min
Enterprise$499/meseDedicated VPC, 10.000 req/min, SLA 99.9%

📁 Struttura Repository

metamesh-uga/├── packages/│   ├── gateway/            # Data Plane: API Gateway, Routing, Cache, Proxy, Reliability│   ├── discovery/          # Control Plane: Discovery Engine│   ├── registry/           # Control Plane: Registry Engine (federation, mirroring, snapshot)│   ├── trust/              # Control Plane: Trust Engine│   ├── security/           # Control Plane: Security Scanner│   ├── policy/             # Control Plane: Policy Engine│   ├── benchmark/          # Control Plane: Benchmark Engine│   ├── lifecycle/          # Control Plane: Lifecycle Manager│   ├── recommendation/     # Control Plane: Recommendation Engine│   ├── cost/               # Control Plane/Data Plane: Cost Optimizer│   ├── compatibility/      # Control Plane: Compatibility Engine│   ├── intelligence/       # Control Plane: AI Intelligence Layer│   ├── analytics/          # Control Plane: Analytics Engine│   ├── health/             # Data Plane: Health Engine│   ├── config/             # Control Plane: Config Engine│   ├── cache/              # Data Plane: Advanced Cache Engine│   ├── self-healing/       # Data Plane: Self-Healing Engine│   ├── aggregator/         # Motore di aggregazione│   ├── inserter/           # Motore di inserimento│   ├── updater/            # Motore di aggiornamento│   ├── eliminatore/        # Motore di eliminazione│   ├── alerts/             # Alerting Worker│   ├── agent-billing/      # Billing per AI Agent│   ├── dashboard/            # Cloudflare Pages (React)│   └── landing/            # Landing page├── cli/                    # CLI Tool (Go)├── shared/                 # Librerie condivise│   ├── src/│   │   ├── auth.js         # Autenticazione│   │   ├── ratelimit.js    # Rate limiting│   │   ├── wasm-runtime.js # WASM execution│   │   └── x402.js         # x402 Protocol│   └── migrations/         # Database migrations├── docs/                   # Documentazione└── wrangler.toml           # Configurazione Cloudflare

🔧 Configurazione Environment

bash
# .envCLOUDFLARE_API_TOKEN=xxxCLOUDFLARE_ACCOUNT_ID=xxxD1_DATABASE_ID=xxxJWT_SECRET=xxxSTRIPE_SECRET_KEY=sk_test_xxxSTRIPE_WEBHOOK_SECRET=whsec_xxxTELEGRAM_BOT_TOKEN=xxxTELEGRAM_CHAT_ID=xxx

🧪 Testing

bash
# Test localewrangler dev --config packages/gateway/wrangler.toml
# Test APIcurl http://localhost:8787/health

📝 Licenza

MIT License - vedi LICENSE

👤 Autore

Davanzo Keoma - GitHub

Il "set & forget" è realtà. 🚀

來源：README.md，提交 b2e7d1f

工具

15

metamesh.context

Compact snapshot of the MetaMesh gateway: active tool count, top categories, payment/billing status, last discovery. Best first call for context.

無需輸入參數。

metamesh.search_tools

Search the catalog of 13k+ MCP tools by keyword. Returns concise matches (name, category, description). Use this instead of listing all tools.

輸入參數q必填limit

metamesh.tool_info

Detailed info for a specific catalog tool: description, category, trust/security score, state, source.

輸入參數name必填

metamesh.metrics

Usage analytics: total tools, calls, success rate and recent error counts. Read-only.

無需輸入參數。

metamesh.discovery_status

Control/observability: status of the registry discovery engine (active tools, last run, pages fetched).

無需輸入參數。

metamesh.health

Gateway health: database connectivity, payment configuration and feature flags.

無需輸入參數。

stripe.stripe_implementation_planner

Stripe integration planner. Use this tool to help users accept payments, sell products online, set up billing, set up a marketplace or platform, or build any Stripe integration. C…

輸入參數acceptmessageguide_idselected_leaf_nodes

stripe.send_stripe_feedback

Share feedback about Stripe's products. Submit when the user gives product feedback or you observe something concrete that worked or failed. Do not report model behavior, the use…

輸入參數actorcontext必填message必填sentiment必填feature_area

stripe.search_stripe_documentation

Search the Stripe documentation for the given question and language. It takes two arguments: - question (str): The user question to search an answer for in the Stripe documentati…

輸入參數languagequestion必填search_only_api_ref

stripe.get_stripe_account_info

This will get the account info for the logged in Stripe account.

無需輸入參數。

stripe.stripe_api_details

Get detailed parameter information for a specific Stripe API operation. Provide the stripe_api_operation_id from stripe_api_search results to see all path, query, and body paramet…

輸入參數stripe_api_operation_id必填

stripe.stripe_api_read

Read data from any Stripe API GET operation: 1. Use stripe_api_search to find the operation ID. 2. Use stripe_api_details to see its parameters, unless the search result already l…

輸入參數parametersstripe_api_operation_id必填

stripe.stripe_api_write

Write data via any Stripe API POST/PATCH/PUT/DELETE operation: 1. Use stripe_api_search to find the operation ID. 2. Use stripe_api_details to see its parameters, unless the searc…

輸入參數parametershuman_confirmationstripe_api_operation_id必填

stripe.stripe_analytics

This tool is for analyzing Stripe Sigma and Metrics data (e.g. about revenue, charges, products, invoices, subscriptions, disputes, transactions, tax tables, payments etc) and run…

輸入參數intent必填params

版本歷史

1
  1. v2.0.3最新Sep 16, 2026

評分

已滿足適用檢查項的 90%

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 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。