Metadata-Version: 2.4
Name: grounder-mcp
Version: 0.1.1
Summary: Current Google answers (Search + AI Overview + AI Mode) as MCP tools for local LLMs and agents.
Project-URL: Homepage, https://grounder.dev
Keywords: mcp,google,ai-overview,ai-mode,search,llm,ollama,lm-studio
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: mcp>=1.2
Requires-Dist: httpx>=0.27

# Grounder

From training data to current knowledge. Gives a local LLM or agent Google's live
answers - the real **AI Overview**, **AI Mode**, and organic **Search** with citations -
as three MCP tools. Privacy-first: the hosted service stores no query content.

This package is a thin MCP client; the scraping and billing run on the hosted service,
so it installs with no Playwright and runs fine on a laptop.

## Use

```json
{
  "mcpServers": {
    "Grounder": {
      "command": "uvx",
      "args": ["grounder-mcp"],
      "env": { "GROUNDER_API_KEY": "your_key_here" }
    }
  }
}
```

Get a key at https://grounder.dev. Tools: `google_search`, `google_ai_overview`,
`google_ai_mode` - one credit per call.
