# Vellm MCP server

> Create AI dance and trend videos from your photos using Vellm templates, and check credits and finished videos.

- Listing: https://mcp.tc/i/vellm
- Connect: use the server's own URL `https://api.vellm.app/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: Vellm
- Homepage: <https://vellm.app/>

## About

Vellm turns one to three photos into short AI videos based on TikTok and Reels trends. The server lets an assistant browse templates, check the credit balance, prepare photo uploads, start a video generation and look up finished videos.

It runs as a hosted Streamable HTTP endpoint at https://api.vellm.app/mcp. Access needs a Vellm account and OAuth sign-in with scopes vellm:read and vellm:create. Video generation spends paid Vellm credits.

## What it can do

- List available video templates
- Check your credit balance
- Prepare photo uploads for a template
- Start a video generation from a template
- Fetch the status and result of a video
- List your previous videos

## Example prompts

- "Show me the Vellm templates that work for a dog photo."
- "How many Vellm credits do I have left?"
- "Create a video from this cat photo with the Tecktonik Cat Dance template."
- "List my recent Vellm videos and their status."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http vellm https://api.vellm.app/mcp
```

2. Start Claude Code, type `/mcp`, pick **vellm** and choose **Authenticate**. A browser window opens for the Vellm sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Vellm** and paste this URL:

```url
https://api.vellm.app/mcp
```

3. Click **Add**, then **Connect**, and sign in when Vellm asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Vellm&connectorUrl=https%3A%2F%2Fapi.vellm.app%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://api.vellm.app/mcp` and click **Add**.

3. Click **Connect** and sign in when Vellm asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://api.vellm.app/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Vellm to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=vellm&config=eyJ1cmwiOiJodHRwczovL2FwaS52ZWxsbS5hcHAvbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "vellm": {
      "url": "https://api.vellm.app/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=vellm&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.vellm.app%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"vellm","type":"http","url":"https://api.vellm.app/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "vellm": {
      "type": "http",
      "url": "https://api.vellm.app/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "vellm": {
      "serverUrl": "https://api.vellm.app/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add vellm --url https://api.vellm.app/mcp
codex mcp login vellm
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.vellm]
url = "https://api.vellm.app/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http vellm https://api.vellm.app/mcp
```

Then, inside Gemini CLI, run `/mcp auth vellm` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "vellm": {
      "type": "http",
      "url": "https://api.vellm.app/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.vellm.app/mcp`.

## Details

- Last checked: 2026-10-24 (reachable, asks for credentials)
- Listed: 2026-10-19
- Updated: 2026-10-19

---
Source: https://mcp.tc/i/vellm (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report