{"id":"5cd83b31-c7ad-4671-871e-0dd45c0da695","slug":"open-ai-ads-agent","kind":"mcp","name":"open-ai-ads-agent","summary":"An AI agent for paid media — ad intelligence, creative testing, and ROAS optimization across PPC, paid social, and programmatic — backed by real ad-platform APIs.","owner":"SamurAIGPT","repoUrl":"https://github.com/SamurAIGPT/open-ai-ads-agent","license":"MIT","licenseTier":"permissive","trust":"community","stars":3,"match":null,"fewStars":true,"format":"mcp","createdAt":"2026-08-26T18:05:49.000Z","addedAt":"2026-10-21T09:33:59.345Z","logoUrl":"https://avatars.githubusercontent.com/u/131431084?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","data-analytics"],"tags":["ad-intelligence","ad-optimization","agency-agents-os","ai-agent","ai-tools","campaign-analytics","creative-testing","digital-advertising"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-26T23:09:39.813Z","sample":false,"url":"https://conduits.dev/tools/open-ai-ads-agent","language":"","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# AI Ads Agent\n\nAn AI agent for paid media — ad intelligence, creative testing, and ROAS optimization across PPC, paid social, and programmatic — backed by real ad-platform APIs.\n\nPart of [Agency Agents OS](https://github.com/Anil-matcha/agency-agents-os), an open ecosystem of specialized AI agents for real business work.\n\n## Related Projects\n\n- [Agency Agents OS](https://github.com/Anil-matcha/agency-agents-os) — the central catalog this repo is part of.\n- [ai-marketing-agent](https://github.com/SamurAIGPT/ai-marketing-agent) — organic counterpart to this repo's paid-media sub-agents.\n- [ai-competitor-intelligence-agent](https://github.com/SamurAIGPT/ai-competitor-intelligence-agent) — shares this repo's ad-library-mining capability for cross-cutting audits.\n- [ai-video-agent](https://github.com/SamurAIGPT/ai-video-agent) — its ad-creative-remake sub-agent regenerates the creative this repo flags as underperforming.\n- [ai-image-agent](https://github.com/SamurAIGPT/ai-image-agent) — generates static ad creative variants.\n- [MuAPI MCP docs](https://muapi.ai/docs/mcp) — connect this repo's `SKILL.md` files via MCP.\n- [MuAPI access keys](https://muapi.ai/access-keys) — create the API key this agent needs.\n\n## What this covers\n\nThis repo is the umbrella for anything an agency or in-house team would call \"the AI ads agent\": watching what competitors are running, structuring and reading creative A/B tests, and turning spend/return data into a budget reallocation recommendation.\n\nPaid media is deliberately its own umbrella here, separate from organic content at [`ai-marketing-agent`](https://github.com/SamurAIGPT/ai-marketing-agent). At a real agency, paid media is run as its own service line — different stakeholders, different cadence, different budget accountability — so it gets its own agent rather than being folded into content/social work.\n\n## Sub-agents\n\n| Agent | Does | Status |\n|---|---|---|\n| [Ad Intelligence](agents/ad-intelligence/SKILL.md) | Mines public ad-library-style data to see what competitors are running, in what formats, and for how long | Blueprint |\n| [Creative Testing](agents/creative-testing/SKILL.md) | Structures and analyzes A/B creative tests across ad variants | Coming Soon |\n| [ROAS Optimization](agents/roas-optimization/SKILL.md) | Analyzes spend/return data across campaigns and recommends budget reallocation | Coming Soon |\n\n## Required Muapi APIs\n\n- `ads.campaign_performance` — spend, return, and efficiency metrics across campaigns.\n- `ads.ad_library_search` — public ad-library-style search for competitor creative and run duration.\n- `ads.creative_metrics` — per-variant creative performance for A/B testing.\n\nSee each sub-agent's `SKILL.md` for the specific capabilities it uses.\n\n## Setup\n\n1. Create a Muapi account and API key at [muapi.ai](https://muapi.ai).\n2. Review the [Muapi API quickstart](https://muapi.ai) and [OpenAPI schema](https://api.muapi.ai/openapi.json) for the ads endpoints.\n3. Load the `SKILL.md` for the sub-agent you need into your agent runtime (hosted agent, MCP client, or custom LLM app), or follow it manually.\n\n\n## Using with an AI agent\n\nEvery sub-agent's `SKILL.md` is model- and runtime-agnostic — it's plain Markdown, so it works with any LLM agent, not just Claude. Two integration paths:\n\n**As an MCP connection (the agent gets live Muapi tools):**\n\nMuapi runs an MCP server at `https://api.muapi.ai/mcp` that any MCP-compatible client can connect to — Cursor, Windsurf, Claude, or your own custom agent.\n\n- **Cursor / Windsurf / other clients with a header field:** connect to `https://api.muapi.ai/mcp` with an `Authorization: Bearer YOUR_MUAPI_KEY` header.\n- **claude.ai / Claude Cowork / other connector UIs with no header field:** use the URL-embedded key form instead, `https://api.muapi.ai/mcp/YOUR_MUAPI_KEY`, via Settings → Connectors → Add custom connector.\n- **Claude Code / Claude Desktop:** `claude mcp add muapi -e MUAPI_API_KEY=YOUR_MUAPI_KEY -- muapi mcp serve` (uses the muapi CLI's stdio transport — Claude Code's HTTP MCP client doesn't reliably inject tools).\n\nFull setup details for every client: [muapi.ai/docs/mcp](https://muapi.ai/docs/mcp).\n\n**As agent instructions (any LLM follows the workflow directly):**\n\nDrop a sub-agent's `SKILL.md` into a Claude Code project's `.claude/skills/` directory, paste it into a custom-GPT/Project's system instructions, hand it to an autonomous agent framework as a tool spec, or attach it directly in a chat conversation — then ask the agent to follow it.\n\n## Read-only vs. write actions\n\nEvery action in this repo is `read-only` or `draft-only` — analysis, reports, and recommended budget splits, not live changes. Changing live campaign budgets, pausing ads, or pushing spend changes to an ad platform is explicitly out of scope for this repo; a human operator applies any recommendation through the ad platform's own console.\n\n## Status and limitations\n\n**Ad Intelligence is Blueprint**: its workflow and decision rules are fully built against `ads.ad_library_search` (public ad-transparency search across Meta, Google, TikTok, and LinkedIn), but that capability is coded and not yet live on Muapi's production API — see its own `SKILL.md` for the exact scope (currently-visible listings only, no date-range filtering, no spend/impression data). **Creative Testing and ROAS Optimization remain Coming Soon**: they depend on `ads.creative_metrics`/`ads.campaign_performance`, which require the official Google Ads/Meta Ads APIs OAuth'd per advertiser's own ad account — a different, larger integration than public ad-library search, and not yet started.\n\n## Contributing\n\nSee [Agency Agents OS CONTRIBUTING.md](https://github.com/Anil-matcha/agency-agents-os/blob/main/CONTRIBUTING.md).\n\n## License\n\n[MIT](LICENSE)\n"}