Metadata-Version: 2.5
Name: aeokit-mcp
Version: 0.1.0
Summary: Measure whether AI answer engines recommend your product. An MCP server for live AEO measurement.
Project-URL: Homepage, https://aeokit.ai
Project-URL: Source, https://github.com/tayden-b/aeokit
Author: Tayden Barretto
License: MIT
License-File: LICENSE
Keywords: aeo,ai-search,answer-engine-optimization,geo,llm,mcp
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
Requires-Python: >=3.10
Requires-Dist: anthropic>=0.40
Requires-Dist: certifi
Requires-Dist: google-genai>=1.0
Requires-Dist: mcp>=2.0
Requires-Dist: openai>=1.40
Requires-Dist: pydantic>=2.0
Requires-Dist: python-dotenv>=1.0
Description-Content-Type: text/markdown

# aeokit-mcp

Measure whether AI answer engines recommend your product.

When a buyer asks ChatGPT, Claude, Gemini, or Perplexity for a tool, the engine names specific products. `aeokit` measures whether it names yours — live, repeatedly, with the statistics to say how confident that is, and the cited pages behind it.

```bash
claude mcp add aeokit --env AEOKIT_USER_OPENAI_API_KEY=sk-... -- uvx aeokit-mcp
```

Then ask your agent: *"I sell Acme, invoicing for freelancers. Do AI assistants recommend us?"*

Runs on **your** API keys. Keys are read only from the server environment — never accepted as tool parameters, because tool arguments land in conversation transcripts.

Full docs: https://aeokit.ai
