# Runway MCP server > Generate images and videos with Runway and partner models from inside your agent, using your Runway plan credits. - Listing: https://mcp.tc/i/runway - Connect: use the server's own URL `https://mcp.runwayml.com/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: Runway - Homepage: ## About Connects Runway to MCP-compatible agents and coding tools so you can generate images and videos from a conversation. You can pass a product URL, a reference image or a text prompt, and the result comes back in the same window. Runway lists models such as Gen-4.5, Seedance 2.0, GPT Image 2, Kling 3.0 and Nano Banana Pro. Runs as a hosted streamable HTTP endpoint at https://mcp.runwayml.com/mcp. Add it as a custom connector in Claude, ChatGPT, Cursor or another MCP client and sign in with your Runway account through OAuth. No separate API key is needed, and generations are tied to your existing Runway plan. ## What it can do - Generate images from text prompts or reference images - Generate videos from text, images or a product URL - Choose between Runway and partner models - Create marketing and product visuals inside your agent - Produce visual assets while building apps and sites ## Example prompts - "Use Runway to make a short marketing video from this product page URL." - "Generate a hero image for my landing page with Runway." - "Create a character-led product ad from this line of dialogue and scene." - "Make several new visuals from this product image to use on my website." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http runway https://mcp.runwayml.com/mcp ``` 2. Start Claude Code, type `/mcp`, pick **runway** and choose **Authenticate**. A browser window opens for the Runway sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Runway** and paste this URL: ```url https://mcp.runwayml.com/mcp ``` 3. Click **Add**, then **Connect**, and sign in when Runway 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]() (opens connector settings) 2. Check that the URL reads `https://mcp.runwayml.com/mcp` and click **Add**. 3. Click **Connect** and sign in when Runway 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://mcp.runwayml.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Runway to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "runway": { "url": "https://mcp.runwayml.com/mcp" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"runway","type":"http","url":"https://mcp.runwayml.com/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "runway": { "type": "http", "url": "https://mcp.runwayml.com/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": { "runway": { "serverUrl": "https://mcp.runwayml.com/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 runway --url https://mcp.runwayml.com/mcp codex mcp login runway ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.runway] url = "https://mcp.runwayml.com/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http runway https://mcp.runwayml.com/mcp ``` Then, inside Gemini CLI, run `/mcp auth runway` 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": { "runway": { "type": "http", "url": "https://mcp.runwayml.com/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://mcp.runwayml.com/mcp`. ## Details - Last checked: 2026-10-03 (reachable, asks for credentials) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/runway (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report