OrbiAds
173 tools to automate Google Ad Manager — campaigns, creatives, inventory, reporting via natural language
README
OrbiAds — Google Ad Manager MCP
A skill for Claude, ChatGPT, Gemini, and OpenAI Codex that gives your AI assistant direct access to Google Ad Manager.
→ Get started free at orbiads.com · ★ Star this repo
Install the skill
Claude Code (CLI) — one command:
./install.sh claude # current project
./install.sh claude --global # all projects
./install.sh skills # load all 8 skills for this session
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"orbiads": {
"type": "http",
"url": "https://orbiads.com/mcp"
}
}
}
claude.ai — Settings → Integrations → Add MCP server → https://orbiads.com/mcp
ChatGPT — Settings → Connectors → Create connector → MCP URL: https://orbiads.com/mcp
Gemini / AI Studio — Tools → MCP configuration → https://orbiads.com/mcp
OpenAI Codex — copy openai-codex/AGENTS.md and openai-codex/mcp/config.remote.json to your workspace root
→ Full guides: Claude · ChatGPT · Gemini · OpenAI Codex
What is OrbiAds?
OrbiAds is a hosted MCP server that connects your AI assistant directly to Google Ad Manager (GAM). Instead of clicking through the GAM interface or writing API scripts, you describe what you want in plain language — OrbiAds handles the API calls, guardrails, and audit trail.
You: "Check inventory availability on the homepage banner for a 300x250 in France next week"
OrbiAds: [runs forecast] → Available: 1.2M impressions. Pressure: low. Safe to traffic.
You: "Create the line item for Renault, €15 CPM, Monday to Friday"
OrbiAds: [applies guardrails] → Preview ready. Confirm to push?
No scripts. No API tokens to manage. No switching tabs.
Who is this for?
- AdOps managers who traffic campaigns daily and want to move faster without making mistakes
- Publishers who manage their own GAM network and want AI-assisted workflows
- Media agencies running multiple GAM accounts who want a consistent, auditable process
- Developers building AdOps automation on top of Claude, ChatGPT, or Gemini
Supported AI Platforms
| Platform | Setup guide | Mode |
|---|---|---|
| Claude (Desktop / claude.ai) | docs/install/claude.md | Plugin + MCP remote |
| ChatGPT (Pro connector) | docs/install/chatgpt.md | MCP remote (HTTP) |
| Gemini | docs/install/gemini.md | Extension + MCP fallback |
| OpenAI Codex | docs/install/openai-codex.md | AGENTS.md + MCP wiring |
All platforms connect to the same hosted MCP endpoint at https://orbiads.com/mcp.
8 Built-in Skills
Each skill is a guided, guardrailed workflow. Your AI assistant loads them on demand.
| Skill | What it does |
|---|---|
bootstrap |
Connect your GAM account, verify credentials, select network |
inventory-ad-units |
Browse and query ad units, placements, and targeting keys |
availability-forecast |
Check inventory availability before trafficking — no writes |
advertiser-order-line-items |
Create and manage advertisers, orders, and line items |
placements-targeting |
Build and verify targeting configurations |
native-image |
Traffic native and image creatives with inline upload |
qa-preview |
Preview and coverage check before any live push |
deploy-reporting |
Deploy with dry-run protection + post-push delivery reports |
5 Composed Workflows
End-to-end workflows that chain skills automatically.
| Workflow | Description |
|---|---|
inventory-to-placement |
From ad unit discovery to targeting-ready placement |
image-to-native |
Upload image → create native creative → traffic line item |
image-to-html5 |
Same flow for HTML5 display creatives |
audio-video-trafficking |
Audio/video line item setup with format guardrails |
deploy-to-reporting |
Push campaign + monitor delivery + generate report |
Safety by Design
Every write action requires explicit confirmation. No campaign goes live by accident.
- Dry-run mode on all deployment actions — preview before you push
- Forecast gate before inventory commits — availability verified upfront
- Audit trail on every action — who did what, when, with what result
- Credit guard — read operations are always free, writes deduct credits transparently
Quick Start (3 steps)
1. Create your free account
Go to orbiads.com and sign up. You get 5 free credits — no credit card required.
2. Connect Google Ad Manager
From the OrbiAds dashboard, click Connect GAM and authorize with your Google account. OrbiAds uses OAuth — your GAM credentials never leave Google's infrastructure.
3. Configure your AI assistant
Pick your platform and follow the guide:
Then start with:
"Connect to my GAM account and show me my active networks"
MCP Server Details
| Property | Value |
|---|---|
| Endpoint | https://orbiads.com/mcp |
| Transport | streamable-http (default) · sse · stdio (local dev only) |
| Auth | OAuth 2.0 — Google account via OrbiAds |
| GAM API version | v202602 |
| MCP Protocol | 2025-03-26 |
Repository Structure
shared/ ← Canonical skills, agents, prompts, workflows, JSON schemas
docs/ ← Installation guides, safety rules, tool matrix, query library
claude-plugin/ ← Claude plugin packaging (manifest, system prompt, router)
openai-codex/ ← AGENTS.md + router for OpenAI/Codex workspaces
gemini-extension/ ← Gemini extension descriptor + function declarations
Business logic lives in
shared/. Platform wrappers are thin adapters that point back to it.
Pricing
| Plan | Price | Credits |
|---|---|---|
| Trial | Free | 5 credits (no card) |
| Starter | €39/month | 50 credits/month |
| Early Access | €29/month ← locked for life | 50 credits/month |
| Pack S | €29 one-time | +50 credits |
| Pack L | €45 one-time | +100 credits |
Reads are always free. Credits are only consumed on write and deploy operations.
License
This repository contains the MCP distribution scaffold and platform integration guides for OrbiAds. The OrbiAds MCP server and backend are proprietary — see terms at orbiads.com.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。