Metadata-Version: 2.4
Name: vee3-mcp
Version: 0.1.0
Summary: Vee3 MCP server for Cursor — website screenshot capture
Project-URL: Homepage, https://vee3.io
Project-URL: Documentation, https://app.vee3.io/dashboard/keys
Project-URL: Repository, https://github.com/1m1ke11/Vee3
Project-URL: Issues, https://github.com/1m1ke11/Vee3/issues
Author: Vee3
License-Expression: MIT
Keywords: agents,cursor,mcp,screenshot,vee3
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.12
Requires-Dist: httpx>=0.28.0
Requires-Dist: mcp>=1.12.0
Requires-Dist: truststore>=0.10.0
Description-Content-Type: text/markdown

# vee3-mcp

MCP server for [Vee3](https://vee3.io) — capture website screenshots from Cursor Agent.

## Cursor setup

1. Install [uv](https://docs.astral.sh/uv/getting-started/installation/)
2. Create an API key at [app.vee3.io/dashboard/keys](https://app.vee3.io/dashboard/keys)
3. Set `VEE3_API_KEY` in your environment
4. Use the **Add to Cursor** button on the dashboard, or add to `~/.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "vee3": {
      "command": "uvx",
      "args": ["vee3-mcp"],
      "env": {
        "VEE3_API_URL": "https://api.vee3.io",
        "VEE3_API_KEY": "${env:VEE3_API_KEY}"
      }
    }
  }
}
```

## Environment variables

| Variable | Required | Default |
|---|---|---|
| `VEE3_API_KEY` | Yes | — |
| `VEE3_API_URL` | No | `https://api.vee3.io` |

## Publish to PyPI

From the repo root, after setting `PYPI_API_TOKEN`:

```powershell
cd mcp
uv build
uv publish --token $env:PYPI_API_TOKEN
```

Then set `NEXT_PUBLIC_MCP_USE_PYPI=true` on Vercel so the dashboard install link uses `uvx vee3-mcp` instead of the Git source.
