About adtest-mcp
adtest-mcp exposes AdTest.AI ad analysis to Claude and other MCP clients, scoring image, video, or text adverts across 13 dimensions.
Key features
- 01Analyze images, videos, and ad copy
- 02Score across 13 dimensions
- 03Return detailed scoring reports
- 04Accept public URLs or local files
- 05Process video analysis asynchronously
Use cases
- 01Evaluate image ads before launch
- 02Review video ad creative
- 03Compare scores for ad copy
MCP support
The MCP server provides the analyze_advert tool to clients, accepting an advert URL, local file path, or text and returning an analysis report.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y adtest-mcpADTEST_API_KEYSecretAdTest.AI developer API key (app.adtest.ai → Developer → Generate key). Each successful analysis costs 1 credit.ADTEST_API_BASEOptional API base URL override (default https://app.adtest.ai/adtest-api).ADTEST_POLL_TIMEOUT_MSOptional max wait for a job in milliseconds (default 900000 = 15 min).Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
1Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | No | Public URL of an image or video advert |
| text | string | No | Ad copy text to analyze |
| brand_url | string | No | Advertiser brand/website URL (optional) |
| file_path | string | No | Local path to an image or video file to upload |
Details
From the project READMEAdTest.AI MCP server
· Registry name:
ai.adtest/adtest-mcp · License: MIT
Adds a single analyze_advert tool to Claude (Desktop, Code, or any MCP client) that
runs AdTest.AI's AI-only 13-dimension analysis of an advert — image, video, or text —
and returns a detailed scoring report. (Human-panel validation is available in the
web app only, not through this server.)
Quick add for Claude Code:
claude mcp add adtest -e ADTEST_API_KEY=adk_your_key_here -- npx -y adtest-mcp
Setup
-
Get an API key: sign in at https://app.adtest.ai → the Developer (gear) icon → Generate key. Make sure your wallet has funds — each successful analysis costs $1.
-
Add the server to your Claude config (Claude Desktop:
claude_desktop_config.json; Claude Code:.mcp.json):{ "mcpServers": { "adtest": { "command": "npx", "args": ["-y", "adtest-mcp"], "env": { "ADTEST_API_KEY": "adk_your_key_here" } } } }Or run it from a local checkout (after
npm installin this folder):{ "mcpServers": { "adtest": { "command": "node", "args": ["/absolute/path/to/mcp-server/index.js"], "env": { "ADTEST_API_KEY": "adk_your_key_here" } } } } -
Restart Claude, then just ask:
- “Analyze this advert: https://example.com/ad.jpg”
- “Analyze this ad video file: /Users/me/promo.mp4”
- “Score this ad copy: 50% off all shoes this weekend — shop now.”
The tool
analyze_advert — provide one of:
| arg | meaning |
|---|---|
url | public URL of an image or video advert (we download it) |
file_path | local image/video file to upload |
text | ad copy to analyze |
brand_url (optional) | advertiser website — improves brand/logo detection |
Returns the AI analysis text plus the amount charged and your remaining balance.
How it works (async — so video works)
The server submits the job to POST /developer/ai-analysis/jobs, gets a
job_id back immediately, then polls GET /developer/ai-analysis/jobs/{job_id}
every few seconds until it's complete or failed. This is why video works:
a single synchronous request would be cut off by the CDN edge timeout (~100s),
but video analysis can take several minutes. You're charged once, on success,
when the job completes — a failed job is never billed.
Notes
-
Registered in the official MCP Registry as
ai.adtest/adtest-mcp. -
Auth is the
x-api-keyheader, set fromADTEST_API_KEY. -
Endpoint defaults to
https://app.adtest.ai/adtest-api; override withADTEST_API_BASEfor staging. -
Poll ceiling defaults to 15 min; override with
ADTEST_POLL_TIMEOUT_MS(milliseconds) for very long video. -
Rate limits: 30 submits/min and 2000/day per key (60/min per IP); polling is generous (240/min) and handled for you.
-
Errors come back as readable text:
invalid_api_key,insufficient_funds,no_creative,invalid_url,unsupported_media_type,too_many_requests,analysis_failed(the last is not charged). -
Requires Node ≥ 18.
Links
- Product: https://adtest.ai
- Setup guide and FAQ: https://adtest.ai/mcp/
- App and API keys: https://app.adtest.ai
- Issues: https://github.com/menaker/adtest-mcp/issues
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.