Open Advertising MCP Server

Cesteral MCP Servers

Self-hostable MCP connectors for major advertising platforms.

Use this repo when you want transparent platform integrations, local experimentation, and infrastructure you control. Use Cesteral Intelligence when your team needs approvals before spend commits, credential brokering, auditability, and cross-platform execution from one governed environment.

Try Meta Ads MCP locally (~10 min) | Compare OSS vs Cesteral Intelligence | Book a workflow demo

---

Start With One Workflow

This repo should be read as an open connector layer, not as the full product.

• Primary launch pair: Google Ads + Meta Ads
• Primary wedge: AI-managed optimization with human approval
• Secondary proof of depth: DV360

If you just need direct platform access, self-host a connector. If the workflow needs approvals, credential control, audit trails, or cross-platform coordination, that is the handoff point to Cesteral Intelligence.

Choose Your Path

• Use OSS connectors when you want transparency, self-hosting, and direct control of credentials and infrastructure.
• Use Cesteral Intelligence when you need governed writes, team approvals, credential brokering, auditability, and multi-platform execution.

---

Flagship Connectors

Google Ads MCP

Campaign writes, GAQL reporting, bid adjustments, previews, and validation via Google Ads REST API v23.

Package docs | Use with Cesteral Intelligence

Meta Ads MCP

Campaign writes, insights, targeting discovery, delivery estimates, previews, and bulk operations via Meta Marketing API v25.0.

Package docs | Use with Cesteral Intelligence

DV360 MCP

Campaign writes, targeting, custom bidding, previews, uploads, and schema-driven validation via DV360 API v4.

Package docs | Use with Cesteral Intelligence

---

When You Need Cesteral Intelligence

The OSS connectors give you per-server tool execution + audit logs. Cesteral Intelligence layers governance and orchestration on top:

• Credential brokering -- keep platform secrets out of local operator workflows
• Approval workflows -- require human review before destructive or high-spend changes
• Aggregated audit -- unified, cross-server activity feed with provenance, tied to operator identity
• Cross-platform orchestration -- coordinate governed execution across multiple connectors
• Team operations -- shared workflows, tenant isolation, and operator visibility

Compare OSS connectors vs Cesteral Intelligence

---

The Full Fleet

---

Built for Production

Self-hosting an AI agent that touches live ad spend is a trust problem first and a capability problem second. Two things make this fleet shippable to production without hand-rolling guardrails:

• Audit-grade observability. Every tool call is captured as append-only JSONL. Failures additionally capture the full upstream HTTP trail — every request, every retry, every response — with secrets redacted at the source. Query it directly in BigQuery for hosted deployments, or pipe stdout to your existing log stack for self-host. Read the observability guide.
• Destructive-action elicitation gates. 53 destructive tools across all 13 servers prompt the user before deletes, bulk status changes, bid adjustments, budget changes, conversion uploads, and async Workflows batch jobs. Stdio and clients without elicitation support fall back to a documented non-interactive contract. Bulk mutations under 10 items skip the prompt unless they touch a sensitive field (status / budget / bid).

If your security review needs evidence — the redaction list, the field schema, the upstream capture path — all of it is in this repository.

---

Quick Start

For a guided walkthrough, see the 10-minute quickstart.

Prerequisites

• Node.js >= 20.0.0
• pnpm >= 8.0.0 -- npm install -g pnpm
• Docker (for containerization)
• Terraform >= 1.6.0 (for deployment)

1. Clone and install

git clone https://github.com/cesteral/mcp-open-advertising.git
cd mcp-open-advertising
pnpm install

2. Build

pnpm run build

3. Run a server locally

# Start any server using the dev script
./scripts/dev-server.sh gads-mcp    # port 3004
./scripts/dev-server.sh meta-mcp    # port 3005
./scripts/dev-server.sh dv360-mcp   # port 3002

# See each package README for required environment variables

4. Configure your AI agent

{
  "mcpServers": {
    "cesteral-gads": {
      "url": "https://gads.your-domain.com/mcp",
      "apiKey": "your-gads-api-key"
    },
    "cesteral-meta": {
      "url": "https://meta.your-domain.com/mcp",
      "apiKey": "your-meta-api-key"
    }
  }
}

Add as many servers as you need. Each runs independently and can be deployed separately.

5. Deploy

cd terraform
terraform init
terraform apply -var-file=dev.tfvars

See the deployment guide for production setup.

---

Architecture

Cesteral uses a GCP-native architecture with thirteen independently deployable Cloud Run MCP services. Each server exposes the MCP protocol directly via HTTPS on Cloud Run.

Key design decisions:

• Single cloud provider (GCP): Cloud Run, BigQuery, Pub/Sub, Secret Manager -- unified monitoring, ~$150-220/month
• Direct HTTP transport: No edge gateway layer needed
• Independent deployment: Each server can be deployed and scaled separately
• Composable: Use one server or all thirteen -- they work independently or together

Access Model

• Self-hosted: AI clients connect directly to one or more MCP servers
• Cesteral Intelligence: Hosted product layers tenancy, credentials, approvals, orchestration, and governance above the connector fleet

Repository Structure

mcp-open-advertising/
├── packages/
│   ├── gads-mcp/          # Google Ads
│   ├── meta-mcp/          # Meta Ads
│   ├── dv360-mcp/         # DV360
│   ├── ttd-mcp/           # The Trade Desk
│   ├── linkedin-mcp/      # LinkedIn Ads
│   ├── tiktok-mcp/        # TikTok Ads
│   ├── cm360-mcp/         # Campaign Manager 360
│   ├── sa360-mcp/         # Search Ads 360
│   ├── pinterest-mcp/     # Pinterest Ads
│   ├── snapchat-mcp/      # Snapchat Ads
│   ├── amazon-dsp-mcp/    # Amazon DSP
│   ├── msads-mcp/         # Microsoft Ads
│   ├── dbm-mcp/           # Bid Manager (reporting)
│   └── shared/            # Shared auth, telemetry, utilities
├── terraform/             # Infrastructure as Code
├── scripts/               # Deployment and dev automation
└── docs/                  # Documentation and guides

---

Development

# Install dependencies
pnpm install

# Build all packages
pnpm run build

# Run tests
pnpm run test

# Type checking
pnpm run typecheck

# Lint
pnpm run lint

Testing MCP Tools

# Use MCP Inspector
npx @modelcontextprotocol/inspector packages/gads-mcp

# Or use curl
curl -X POST http://localhost:3004/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}'

Technology Stack

• Runtime: TypeScript 5.0+, Node.js 20 LTS, Hono (HTTP + MCP transport)
• Validation: Zod schemas
• Infrastructure: GCP Cloud Run, BigQuery, Pub/Sub, Secret Manager, Terraform
• Build: Turborepo, pnpm workspaces, Docker

---

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

1. Fork the repository
2. Create a feature branch: git checkout -b feature/your-feature
3. Make changes and write tests
4. Run tests: pnpm run test
5. Submit a Pull Request

See also: CODE_OF_CONDUCT.md | SECURITY.md | ROADMAP.md

---

License

Apache License 2.0

---

Support

• Website: cesteral.com -- managed hosting and commercial features
• Documentation: docs/ for guides and architecture
• GitHub Issues: Report bugs or request features
• Email: support@cesteral.com