# ModelRunner

Connect Claude Code to models for image, video, audio, and 3D generation. The agent can search the catalog, inspect model inputs, and run requests.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: modelrunner
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/modelrunner/modelrunner-mcp
- Updated: 2026-09-07
- HTML: https://affpapa.org/en/nevibecode/mcp/modelrunner

## What it does

ModelRunner exposes models from multiple providers through a single remote MCP endpoint. An agent can look up a model, inspect its input schema, submit a generation request, and receive hosted result links. The catalog includes tasks such as turning images into video, generating music, and transcribing speech.

The available tools also cover file uploads and custom wrappers: simplified interfaces built on top of base models. Connecting is free, while model runs draw from prepaid credits. Sign-in happens in a browser on first use; the server is hosted remotely, so there is no local server to install or maintain.

## Requirements
- Remote server: `https://mcp.modelrunner.run/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.modelrunner.run/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add modelrunner --url https://mcp.modelrunner.run/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "modelrunner": {
            "url": "https://mcp.modelrunner.run/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "modelrunner": {
            "type": "http",
            "url": "https://mcp.modelrunner.run/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http modelrunner https://mcp.modelrunner.run/mcp
```

## When to use it
- find a model for image or video generation
- inspect a model's inputs before submitting a request
- generate music or transcribe speech
- upload a file for model processing
- build a simplified wrapper around a base model

## Example prompts
- Find a model that turns an image into video and show its input fields.
- Generate music from this description and return the result link.
- Create a wrapper with simple inputs for the selected model.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 403142
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 34046
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89721
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81203
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74590
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 90224

---
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