Meta Ads MCP Server
MCP server to manage Meta Ads campaigns from any machine, deployable on Railway. Supports campaign management via Meta Marketing API through Claude or other MCP clients.
README
Meta Ads MCP Server - Railway Deploy
Server MCP per gestire le campagne Meta Ads da qualsiasi macchina.
🚀 Deploy su Railway
1. Prerequisiti
- Account Railway (https://railway.app)
- Token di accesso Meta Marketing API
2. Deploy
Opzione A: Deploy da GitHub
- Fai push di questa cartella su un repo GitHub
- Vai su Railway → New Project → Deploy from GitHub
- Seleziona il repository
- Railway farà il deploy automaticamente
Opzione B: Deploy con Railway CLI
# Installa Railway CLI
npm install -g @railway/cli
# Login
railway login
# Crea progetto e deploya
railway init
railway up
3. Configura le Variabili d'Ambiente
In Railway, vai su Settings → Variables e aggiungi:
| Variabile | Descrizione |
|---|---|
META_ACCESS_TOKEN |
Token di accesso Meta Marketing API |
META_APP_SECRET |
(Opzionale) App secret per refresh token |
META_APP_ID |
(Opzionale) App ID per OAuth |
4. Ottieni l'URL
Dopo il deploy, Railway ti fornirà un URL tipo:
https://meta-ads-mcp-production-xxxx.up.railway.app
⚙️ Configura Claude Desktop
Aggiungi questa configurazione a claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"meta-ads": {
"url": "https://TUO-URL-RAILWAY.railway.app/mcp"
}
}
}
📡 Endpoints
| Endpoint | Descrizione |
|---|---|
GET / |
Info server e configurazione |
GET /health |
Health check |
POST /mcp |
Endpoint MCP principale |
GET /sse |
Server-Sent Events |
🔐 Come ottenere il Meta Access Token
- Vai su Meta for Developers
- Crea un'app o usa una esistente
- Vai su Tools → Graph API Explorer
- Seleziona la tua app
- Aggiungi i permessi:
ads_management,ads_read - Genera il token
- (Opzionale) Converti in token a lunga durata
🧪 Test
Verifica che funzioni:
# Health check
curl https://TUO-URL.railway.app/health
# Risposta attesa:
# {"status":"ok","timestamp":"...","service":"meta-ads-mcp"}
💰 Costi Railway
- Piano Free: 500 ore/mese (sufficiente per uso personale)
- Piano Hobby: $5/mese (sempre attivo)
🔧 Troubleshooting
Token scaduto
- Rigenera il token su Meta for Developers
- Aggiorna la variabile
META_ACCESS_TOKENsu Railway
Errori di connessione
- Verifica che l'URL sia corretto (con /mcp alla fine)
- Controlla i log su Railway Dashboard
Permessi insufficienti
- Verifica che il token abbia i permessi
ads_managementeads_read
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.