MetaMesh-UGA

Official15 toolsLive

by SiouxTXT · JavaScript

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

dev.metamesh-uga/metamesh-uga — Model Context Protocol (MCP) Server

Serverless edge control plane that supports MCP infrastructure for discovering, routing, and monetizing 14,982+ MCP tools. Identified as an MCP server with 15 tools reported, and described under the name “MetaMesh-UGA / MetaMesh-UGA.”

🛠️ Key Features

Serverless edge control plane
Discover MCP tools
Route MCP tools
Monetize MCP tools

🚀 Use Cases

Building MCP-based tool access through a gateway/control plane
Managing large sets of MCP tools (14,982+)

⚡ Developer Benefits

Integration with Model Context Protocol (MCP)
Tool-use oriented workflows (llm-tools, tool-use)
Cloudflare Workers–related deployment context (cloudflare-workers)

⚠️ Limitations

Tooling details beyond the count (15) and operational role are not provided in the available excerpt.

mcp toolsdiscoveryroutingedge computingmonetizationserverless

Topics

agentic-paymentsai-agentscloudflare-workersllm-toolsmcpmcp-gatewaymcp-servermodel-context-protocolserverlessstripetool-usex402

Captured live from the server via tools/list.

metamesh.context

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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.

Parameters2

q	string	required	Search query, e.g. "github", "database", "email"
limit	number	optional	Max results (default 10, max 50)

Raw schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Search query, e.g. \"github\", \"database\", \"email\""
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 10, max 50)"
    }
  },
  "required": [
    "q"
  ]
}

metamesh.tool_info

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

Parameters1

name

string

required

Exact tool name

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Exact tool name"
    }
  },
  "required": [
    "name"
  ]
}

metamesh.metrics

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

metamesh.discovery_status

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

metamesh.health

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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…

Parameters3

question	string	required	The user question about integrating with Stripe will be used to search the documentation.
language	string	optional	The programming language to search for in the documentation.
search_only_api_ref	boolean	optional	When set to true, search only in the Stripe API reference documentation instead of the full documentation set. Use true when users need specific API implementation details, code examples, or parameter references. Use false (default) for conceptual explanations, best practices, integration guides, or troubleshooting help.

Raw schema

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "description": "The user question about integrating with Stripe will be used to search the documentation.",
      "maxLength": 1000
    },
    "language": {
      "type": "string",
      "description": "The programming language to search for in the documentation.",
      "enum": [
        "dotnet",
        "go",
        "java",
        "node",
        "php",
        "ruby",
        "python",
        "curl"
      ]
    },
    "search_only_api_ref": {
      "type": "boolean",
      "description": "When set to true, search only in the Stripe API reference documentation instead of the full documentation set. Use true when users need specific API implementation details, code examples, or parameter references. Use false (default) for conceptual explanations, best practices, integration guides, or troubleshooting help."
    }
  },
  "required": [
    "question"
  ]
}

stripe.get_stripe_account_info

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

stripe.create_refund

This tool will refund a payment intent in Stripe.

Parameters4

payment_intent	string	required	The ID of the PaymentIntent to refund.
amount	integer	optional	The amount to refund in currency minor units, e.g. cents for USD and yen for JPY.
reason	string	optional	The reason for the refund.
human_confirmation	object	optional	This tool might require human confirmation. To run it, first invoke it with the desired parameters, ignoring the `approval_token` parameter. If it requires human confirmation, the response will include an approval request ID and a URL to an approval page for the human to approve the tool call. You, as the LLM agent, should: 1. Present this URL to the human as a clickable markdown link. Tell them that they have to approve this tool call at that URL, and that they should tell you when they have approved the operation. 2. The human will approve that call. 3. After the human tells you they have approved the operation, you must call the tool again with the `approval_token` parameter and the exact same parameters. The operation will then go through.

Raw schema

{
  "type": "object",
  "properties": {
    "payment_intent": {
      "description": "The ID of the PaymentIntent to refund.",
      "type": "string"
    },
    "amount": {
      "description": "The amount to refund in currency minor units, e.g. cents for USD and yen for JPY.",
      "type": "integer"
    },
    "reason": {
      "description": "The reason for the refund.",
      "enum": [
        "duplicate",
        "fraudulent",
        "requested_by_customer"
      ],
      "type": "string"
    },
    "human_confirmation": {
      "type": "object",
      "description": "This tool might require human confirmation. To run it, first invoke it with the desired parameters, ignoring the `approval_token` parameter.\nIf it requires human confirmation, the response will include an approval request ID and a URL to an approval page for the human to approve the tool call.\nYou, as the LLM agent, should:\n\n1. Present this URL to the human as a clickable markdown link. Tell them that they have to approve this tool call at that URL, and that they should tell you when they have approved the operation.\n2. The human will approve that call.\n3. After the human tells you they have approved the operation, you must call the tool again with the `approval_token` parameter and the exact same parameters. The operation will then go through.\n",
      "properties": {
        "approval_token": {
          "type": "string",
          "description": "The ID of the approval token for the request. This is required on only the post-human-confirmation invocation. An example ID is `approval_123`."
        }
      }
    }
  },
  "required": [
    "payment_intent"
  ]
}

stripe.stripe_implementation_planner

Stripe payment integration planner. Use this tool to help users accept payments, sell products online, set up billing, or build any Stripe integration. Call this BEFORE writing co…

Parameters3

guide_id	string	optional	ONLY pass a guide_id that was returned by a previous call to this tool in this conversation. Never fabricate, guess, or reuse guide_ids from other sessions. If you do not have a guide_id from a prior response, omit this field entirely. Invalid guide_ids will be rejected.
message	string	required	For new guides: describe the use case or business requirements. For existing guides: provide the latest user response or the full accepted transcript.
accept	boolean	optional	Set to true when returning the completed decision tree with your chosen options to receive the finalized integration guide.

Raw schema

{
  "type": "object",
  "properties": {
    "guide_id": {
      "description": "ONLY pass a guide_id that was returned by a previous call to this tool in this conversation. Never fabricate, guess, or reuse guide_ids from other sessions. If you do not have a guide_id from a prior response, omit this field entirely. Invalid guide_ids will be rejected.",
      "type": "string"
    },
    "message": {
      "description": "For new guides: describe the use case or business requirements. For existing guides: provide the latest user response or the full accepted transcript.",
      "type": "string"
    },
    "accept": {
      "description": "Set to true when returning the completed decision tree with your chosen options to receive the finalized integration guide.",
      "type": "boolean"
    }
  },
  "required": [
    "message"
  ]
}

stripe.send_stripe_mcp_feedback

Submit feedback from user or agent about Stripe's MCP server tools. Valid: "the search tool returned irrelevant results", "I wish there was a tool for X" Invalid: Stripe API comp…

Parameters5

sentiment	string	required	positive, negative, or neutral
quote	string	required	User's exact message containing feedback. Max 1000 chars.
context	string	required	User persona, their broader goal, current task, and estimated technical proficiency.
tool_name	string	optional	The name of the tool the user is giving feedback about. Include if confident that feedback is about a specific tool.
source	string	required	user or agent

Raw schema

{
  "type": "object",
  "properties": {
    "sentiment": {
      "type": "string",
      "enum": [
        "positive",
        "negative",
        "neutral"
      ],
      "description": "positive, negative, or neutral"
    },
    "quote": {
      "type": "string",
      "description": "User's exact message containing feedback. Max 1000 chars.",
      "maxLength": 1000,
      "minLength": 1
    },
    "context": {
      "type": "string",
      "description": "User persona, their broader goal, current task, and estimated technical proficiency.",
      "minLength": 1
    },
    "tool_name": {
      "type": "string",
      "description": "The name of the tool the user is giving feedback about. Include if confident that feedback is about a specific tool."
    },
    "source": {
      "type": "string",
      "description": "user or agent",
      "enum": [
        "user",
        "agent"
      ]
    }
  },
  "required": [
    "sentiment",
    "quote",
    "context",
    "source"
  ]
}

stripe.stripe_api_search

Search for Stripe API operations by providing an intent and a resource to operate on. Returns matching operations with their HTTP method, path, summary, and top-level parameter n…

Parameters3

intent	string	required	The intent of the operation
resource	string	required	Target resource the operation is looking to manipulate
limit	integer	optional	Maximum number of results to return

Raw schema

{
  "type": "object",
  "properties": {
    "intent": {
      "type": "string",
      "description": "The intent of the operation",
      "examples": [
        "create",
        "list",
        "refund"
      ]
    },
    "resource": {
      "type": "string",
      "description": "Target resource the operation is looking to manipulate",
      "examples": [
        "customer",
        "payments",
        "charge"
      ]
    },
    "limit": {
      "description": "Maximum number of results to return",
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "default": 5
    }
  },
  "required": [
    "intent",
    "resource"
  ]
}

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…

Parameters1

stripe_api_operation_id

string

required

The operation ID to get details for (e.g. 'PostCustomers', 'GetPaymentIntents')

Raw schema

{
  "type": "object",
  "properties": {
    "stripe_api_operation_id": {
      "description": "The operation ID to get details for (e.g. 'PostCustomers', 'GetPaymentIntents')",
      "type": "string"
    }
  },
  "required": [
    "stripe_api_operation_id"
  ]
}

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 understand its parameters (required for operations wit…

Parameters2

stripe_api_operation_id	string	required	The operation ID to execute (e.g. 'PostCustomers', 'GetPaymentIntents')
parameters	object	required	Parameters for the API call. Include path parameters (e.g. 'customer' for /v1/customers/{customer}), query parameters, and body parameters as a flat object. Nested object fields use dot-notation (e.g. "address.city"). Array fields (e.g. line_items) must be passed as a JSON array value, not as a plain string.

Raw schema

{
  "type": "object",
  "properties": {
    "stripe_api_operation_id": {
      "description": "The operation ID to execute (e.g. 'PostCustomers', 'GetPaymentIntents')",
      "type": "string"
    },
    "parameters": {
      "description": "Parameters for the API call. Include path parameters (e.g. 'customer' for /v1/customers/{customer}), query parameters, and body parameters as a flat object. Nested object fields use dot-notation (e.g. \"address.city\"). Array fields (e.g. line_items) must be passed as a JSON array value, not as a plain string.",
      "type": "object"
    }
  },
  "required": [
    "stripe_api_operation_id",
    "parameters"
  ]
}

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 understand its parameters (required …

Parameters3

stripe_api_operation_id	string	required	The operation ID to execute (e.g. 'PostCustomers', 'GetPaymentIntents')
parameters	object	required	Parameters for the API call. Include path parameters (e.g. 'customer' for /v1/customers/{customer}), query parameters, and body parameters as a flat object. Nested object fields use dot-notation (e.g. "address.city"). Array fields (e.g. line_items) must be passed as a JSON array value, not as a plain string.
human_confirmation	object	optional	This tool might require human confirmation. To run it, first invoke it with the desired parameters, ignoring the `approval_token` parameter. If it requires human confirmation, the response will include an approval request ID and a URL to an approval page for the human to approve the tool call. You, as the LLM agent, should: 1. Present this URL to the human as a clickable markdown link. Tell them that they have to approve this tool call at that URL, and that they should tell you when they have approved the operation. 2. The human will approve that call. 3. After the human tells you they have approved the operation, you must call the tool again with the `approval_token` parameter and the exact same parameters. The operation will then go through.

Raw schema

{
  "type": "object",
  "properties": {
    "stripe_api_operation_id": {
      "description": "The operation ID to execute (e.g. 'PostCustomers', 'GetPaymentIntents')",
      "type": "string"
    },
    "parameters": {
      "description": "Parameters for the API call. Include path parameters (e.g. 'customer' for /v1/customers/{customer}), query parameters, and body parameters as a flat object. Nested object fields use dot-notation (e.g. \"address.city\"). Array fields (e.g. line_items) must be passed as a JSON array value, not as a plain string.",
      "type": "object"
    },
    "human_confirmation": {
      "type": "object",
      "description": "This tool might require human confirmation. To run it, first invoke it with the desired parameters, ignoring the `approval_token` parameter.\nIf it requires human confirmation, the response will include an approval request ID and a URL to an approval page for the human to approve the tool call.\nYou, as the LLM agent, should:\n\n1. Present this URL to the human as a clickable markdown link. Tell them that they have to approve this tool call at that URL, and that they should tell you when they have approved the operation.\n2. The human will approve that call.\n3. After the human tells you they have approved the operation, you must call the tool again with the `approval_token` parameter and the exact same parameters. The operation will then go through.\n",
      "properties": {
        "approval_token": {
          "type": "string",
          "description": "The ID of the approval token for the request. This is required on only the post-human-confirmation invocation. An example ID is `approval_123`."
        }
      }
    }
  },
  "required": [
    "stripe_api_operation_id",
    "parameters"
  ]
}

README.md17 KBView on GitHub

MetaMesh-UGA

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

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.git
cd metamesh-uga
npm install

2. Configurazione Cloudflare

bash

# Installa Wrangler
npm install -g wrangler

# Login a Cloudflare
wrangler login

# Crea database D1
wrangler d1 create metamesh-catalog

# Crea KV namespace
wrangler kv:namespace create "CACHE"

# Crea R2 bucket
wrangler r2 bucket create metamesh-wasm

3. Configura Secrets

bash

# Stripe
wrangler secret put STRIPE_SECRET_KEY
wrangler secret put STRIPE_WEBHOOK_SECRET

# JWT
wrangler secret put JWT_SECRET

# Alerting (opzionale)
wrangler secret put TELEGRAM_BOT_TOKEN
wrangler secret put TELEGRAM_CHAT_ID

# Admin
wrangler secret put ADMIN_KEY

4. Database Migration

bash

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

5. Deploy

bash

# Deploy Workers
npm run deploy:workers

# Deploy Dashboard
cd packages/dashboard
npm install
npm run deploy

6. Installa CLI

bash

cd cli
go build -o metamesh

# Installa globalmente
mv 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 disponibili
metamesh list --category demo

# Visualizza utilizzo
metamesh usage

API REST

bash

# List tools (paginated, public)
curl "https://api.metamesh-uga.dev/v1/tools?limit=20&sort=popularity"

# Full-text search
curl "https://api.metamesh-uga.dev/v1/search?q=github"

# Execute a tool
curl -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 call
curl -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 / history
curl 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

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).
The agent constructs a signed payment and retries with an X-PAYMENT header (base64 JSON).
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.

code

┌─────────────────────────────────────────────────────────────────────────────┐
│                      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

Piano	Prezzo	Feature
Free	€0	1.000 chiamate/mese, 100 req/min
Pro	$19/mese	Chiamate illimitate, 1.000 req/min
Enterprise	$499/mese	Dedicated VPC, 10.000 req/min, SLA 99.9%

📁 Struttura Repository

code

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

# .env
CLOUDFLARE_API_TOKEN=xxx
CLOUDFLARE_ACCOUNT_ID=xxx
D1_DATABASE_ID=xxx
JWT_SECRET=xxx
STRIPE_SECRET_KEY=sk_test_xxx
STRIPE_WEBHOOK_SECRET=whsec_xxx
TELEGRAM_BOT_TOKEN=xxx
TELEGRAM_CHAT_ID=xxx

🧪 Testing

bash

# Test locale
wrangler dev --config packages/gateway/wrangler.toml

# Test API
curl http://localhost:8787/health

📝 Licenza

MIT License - vedi LICENSE

👤 Autore

Davanzo Keoma - GitHub

Il "set & forget" è realtà. 🚀

Install

Tools (15)

metamesh.contextmetamesh.search_toolsmetamesh.tool_infometamesh.metricsmetamesh.discovery_statusmetamesh.healthstripe.search_stripe_documentationstripe.get_stripe_account_info

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.metamesh-uga.dev/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "metamesh-uga": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.metamesh-uga.dev/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

dev.metamesh-uga/metamesh-uga — Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

metamesh.context

metamesh.search_tools

metamesh.tool_info

metamesh.metrics

metamesh.discovery_status

metamesh.health

stripe.search_stripe_documentation

stripe.get_stripe_account_info

stripe.create_refund

stripe.stripe_implementation_planner

stripe.send_stripe_mcp_feedback

stripe.stripe_api_search

stripe.stripe_api_details

stripe.stripe_api_read

stripe.stripe_api_write

MetaMesh-UGA

Live Status

🚀 Caratteristiche

📋 Requisiti

🛠️ Installazione

1. Clone e Setup

2. Configurazione Cloudflare

3. Configura Secrets

4. Database Migration

5. Deploy

6. Installa CLI

🎯 Uso

CLI Tool

API REST

MCP Protocol

🤖 AI Agent Economy

Model A — Stripe prepaid credit (recommended)

Model B — x402 crypto (USDC on Base)

Payment flow

Activation (operator)

📊 Architettura

💰 Piani di Pagamento

📁 Struttura Repository

🔧 Configurazione Environment

🧪 Testing

📝 Licenza

👤 Autore

Install

Remote endpoint

Related servers