Orbiads

Created By
OrbiAds2 months ago
173 tools to automate Google Ad Manager — campaigns, creatives, inventory, reporting via natural language
Overview

OrbiAds — Google Ad Manager MCP

MCP Protocol GAM API Version Works with Claude Works with ChatGPT Works with Gemini

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

PlatformSetup guideMode
Claude (Desktop / claude.ai)docs/install/claude.mdPlugin + MCP remote
ChatGPT (Pro connector)docs/install/chatgpt.mdMCP remote (HTTP)
Geminidocs/install/gemini.mdExtension + MCP fallback
OpenAI Codexdocs/install/openai-codex.mdAGENTS.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.

SkillWhat it does
bootstrapConnect your GAM account, verify credentials, select network
inventory-ad-unitsBrowse and query ad units, placements, and targeting keys
availability-forecastCheck inventory availability before trafficking — no writes
advertiser-order-line-itemsCreate and manage advertisers, orders, and line items
placements-targetingBuild and verify targeting configurations
native-imageTraffic native and image creatives with inline upload
qa-previewPreview and coverage check before any live push
deploy-reportingDeploy with dry-run protection + post-push delivery reports

5 Composed Workflows

End-to-end workflows that chain skills automatically.

WorkflowDescription
inventory-to-placementFrom ad unit discovery to targeting-ready placement
image-to-nativeUpload image → create native creative → traffic line item
image-to-html5Same flow for HTML5 display creatives
audio-video-traffickingAudio/video line item setup with format guardrails
deploy-to-reportingPush 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

PropertyValue
Endpointhttps://orbiads.com/mcp
Transportstreamable-http (default) · sse · stdio (local dev only)
AuthOAuth 2.0 — Google account via OrbiAds
GAM API versionv202602
MCP Protocol2025-03-26

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

PlanPriceCredits
TrialFree5 credits (no card)
Starter€39/month50 credits/month
Early Access€29/month ← locked for life50 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.

Start free →


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.

Server Config

{
  "mcpServers": {
    "orbiads": {
      "type": "http",
      "url": "https://orbiads.com/mcp"
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
OrbiAds
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

8 hours ago