# ModelsLab MCP server

> Generate images, video, speech, music, and LLM chat responses using over 10,000 AI models through a single interface.

- Repository: https://github.com/ModelsLab/modelslab-mcp
- Page: https://hostedmcp.org/servers/modelslab/modelslab-v8
- Transport: remote
- Stars: 0
- License: MIT
- Latest version: 1.0.0

## Install

### Claude Code

```sh
claude mcp add --transport http modelslab-v8 https://modelslab.com/mcp/v8
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "modelslab-v8": {
      "url": "https://modelslab.com/mcp/v8"
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "modelslab-v8": {
      "type": "http",
      "url": "https://modelslab.com/mcp/v8"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"modelslab-v8","type":"http","url":"https://modelslab.com/mcp/v8"}'
```

### Codex

```sh
codex mcp add modelslab-v8 --url https://modelslab.com/mcp/v8
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.modelslab-v8]
url = "https://modelslab.com/mcp/v8"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http modelslab-v8 https://modelslab.com/mcp/v8
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "modelslab-v8": {
      "url": "https://modelslab.com/mcp/v8",
      "type": "http"
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `MODELSLAB_API_KEY` | no | no |  |

## FAQ

### How do I handle long-running generation tasks?

Most generations are asynchronous; the tool returns a processing status and an ID, which you can then check using the fetch-generation tool.

### What is the pricing for using the MCP server?

MCP calls are billed the same as the REST API, with plans starting at $21 per month.
