# Tanvo

Tanvo lets an agent create images, video clips and songs through the service. Use it to turn a prompt or local photo into a media file from your coding chat.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: tanvoai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/tanvoai/tanvo-mcp
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/mcp/tanvo

## What it does

The server connects an MCP client to Tanvo. An agent can locate a suitable app, send it a prompt or photo, and retrieve the output; generated files can also go to a chosen folder. The available jobs include image creation and editing, photo combinations, video generation and songs.

Its tools cover app and model lookup, generation requests and checking a run's status. Node 20+ is required. Image generation on the service's house engine has a free option without an API key, but those images carry a watermark. Video, songs and apps using premium models need a key. Tanvo receives the prompts and photos for processing, and moderates content before a job runs.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `TANVO_API_KEY`, `TANVO_OUTPUT_DIR` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env TANVO_API_KEY=<TANVO_API_KEY> --env TANVO_OUTPUT_DIR=<TANVO_OUTPUT_DIR> --transport stdio tanvo -- npx -y tanvo-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add tanvo --env TANVO_API_KEY=<TANVO_API_KEY> --env TANVO_OUTPUT_DIR=<TANVO_OUTPUT_DIR> -- npx -y tanvo-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "tanvo": {
            "command": "npx",
            "args": [
                "-y",
                "tanvo-mcp"
            ],
            "env": {
                "TANVO_API_KEY": "<TANVO_API_KEY>",
                "TANVO_OUTPUT_DIR": "<TANVO_OUTPUT_DIR>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "tanvo": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "tanvo-mcp"
            ],
            "env": {
                "TANVO_API_KEY": "<TANVO_API_KEY>",
                "TANVO_OUTPUT_DIR": "<TANVO_OUTPUT_DIR>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e TANVO_API_KEY=<TANVO_API_KEY> -e TANVO_OUTPUT_DIR=<TANVO_OUTPUT_DIR> tanvo npx -y tanvo-mcp
```
Replace <…> with your own values

## When to use it
- turn a pet photo into a portrait
- create an image from a text prompt
- animate a product photo as a video
- write a song around a given subject
- save generated files to a folder

## Example prompts
- Turn `~/Pictures/rex.jpg` into a Renaissance-style portrait of my dog.
- Write a birthday song for Ana about surfing and puns, then save it to `~/Music`.
- Make a slow 360° spin video from this product photo.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
