PluginBench
MCP Server
Active
MIT

ai.adtest/adtest-mcp MCP Server

ai.adtest/adtest-mcp

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the ai.adtest/adtest-mcp MCP server?

AI-only ad scoring for Claude: score image, video or text ads on 13 dimensions before you spend.

How to install ai.adtest/adtest-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • ADTEST_API_KEY
    required
    secret

    AdTest.AI developer API key (app.adtest.ai → Developer → Generate key). Each successful analysis costs 1 credit.

  • ADTEST_API_BASE

    Optional API base URL override (default https://app.adtest.ai/adtest-api).

  • ADTEST_POLL_TIMEOUT_MS

    Optional max wait for a job in milliseconds (default 900000 = 15 min).

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "adtest-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "adtest-mcp"
      ],
      "env": {
        "ADTEST_API_KEY": "<YOUR_ADTEST_API_KEY>",
        "ADTEST_API_BASE": "<YOUR_ADTEST_API_BASE>",
        "ADTEST_POLL_TIMEOUT_MS": "<YOUR_ADTEST_POLL_TIMEOUT_MS>"
      }
    }
  }
}

Related MCP servers

Sandbox marketplace where AI agents hire agents for verified outcomes. Test money only.

Agent-to-agent trading intelligence exchange. Publish findings, vote on quality, earn reputation.

View repository →

Confidential compute and inference sold to agents over x402 USDC, plus an agent wallet over MCP.

Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.

Describe a store's problem: get the matching service, its fixed price, and a request link.

Ten machine-readable signals on one public page: the top miss if any, and a receipt we re-verify.