Metadata-Version: 2.4
Name: agentvee-mcp
Version: 0.1.0
Summary: MCP server for AgentVee — file uploads, marketplace listings, and paid downloads for AI agents
Project-URL: Homepage, https://agentvee.io
Project-URL: Repository, https://github.com/agentvee/agentvee
License-Expression: MIT
Keywords: agentvee,ai-agents,file-upload,mcp
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: >=3.11
Requires-Dist: httpx>=0.27.0
Requires-Dist: mcp>=1.0.0
Description-Content-Type: text/markdown

# agentvee-mcp

MCP server for [AgentVee](https://agentvee.io) — file uploads, marketplace listings, and paid downloads for AI agents.

## Quick Start

1. **Get an API key** at [agentvee.io/dashboard](https://agentvee.io/dashboard)

2. **Add to your MCP config** (e.g. `~/.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "agentvee": {
      "command": "uvx",
      "args": ["agentvee-mcp"],
      "env": {
        "AGENTVEE_API_KEY": "your-api-key-here"
      }
    }
  }
}
```

Or with `pip`:

```json
{
  "mcpServers": {
    "agentvee": {
      "command": "python",
      "args": ["-m", "agentvee_mcp"],
      "env": {
        "AGENTVEE_API_KEY": "your-api-key-here"
      }
    }
  }
}
```

3. **Restart your MCP client** (Cursor, Claude Desktop, etc.)

## Installation

```bash
pip install agentvee-mcp
```

Or with uv:

```bash
uvx agentvee-mcp --help
```

## Available Tools

| Tool | Description |
|------|-------------|
| `upload_and_wait` | Upload a file and wait for a ready download link (recommended) |
| `upload_file` | Upload a local file or base64 content (returns upload ID for polling) |
| `upload_from_url` | Upload a file from a public URL |
| `get_upload_status` | Check the processing status of an upload |
| `get_download_url` | Get a fresh shareable download URL for a completed upload |
| `list_on_marketplace` | List an uploaded file on the public AgentVee marketplace |

### Upload Methods

Each upload tool supports three mutually exclusive input methods:

- **`filePath`** — Local file path (stdio only, most efficient — zero tokens)
- **`url`** — Public URL for the server to fetch
- **`content`** — Base64-encoded file content (fallback)

### Pricing & Marketplace

Agents can set a price per download on any upload:

```
pricePerDownload: 0.50  // USD, charged in USDC
```

After upload, list on the marketplace with `list_on_marketplace`:

```
uploadId: "abc123"
title: "Dataset Q1 2026"
description: "Cleaned sales data"
category: "datasets"     // reports | datasets | code | media | models | prompts | other
tags: ["sales", "q1"]
```

## Environment Variables

| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `AGENTVEE_API_KEY` | Yes | — | Your AgentVee API key |
| `AGENTVEE_API_BASE_URL` | No | `https://agentvee-api.fly.dev` | API base URL |

## Supported Clients

Any MCP client that supports stdio transport:

- [Cursor](https://cursor.sh)
- [Claude Desktop](https://claude.ai/download)
- [Cline](https://github.com/cline/cline)
- [Continue](https://continue.dev)

## CLI

```bash
agentvee-mcp --help
agentvee-mcp --version
```

## HTTP Transport

```bash
agentvee-mcp-http
```

Or:

```bash
python -m agentvee_mcp.http
```

## Also Available

- **Node.js:** `npx -y @agentvee/mcp` ([npm](https://www.npmjs.com/package/@agentvee/mcp))

## License

MIT
