# ElevenLabs MCP server > Manage ElevenLabs voice agents and generate speech, music, sound effects, images and video from your assistant. - Listing: https://mcp.tc/i/elevenlabs - Connect: use the server's own URL `https://api.us.elevenlabs.io/v1/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: ElevenLabs - Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe. - Homepage: - Repository: ## About Connects an assistant to an ElevenLabs workspace. It can create, configure, test and manage voice and chat agents, and generate speech, music, sound effects, images and video. OAuth scopes cover agent read and write, text to speech, speech history, flows, image and video generation, and voice generation. Runs as a hosted streamable HTTP endpoint at https://api.us.elevenlabs.io/v1/mcp. Users sign in with their ElevenLabs account through OAuth. Workspaces with data residency use the regional endpoint for EU, India or Singapore instead. This replaces the archived local elevenlabs-mcp server. ## What it can do - Create, configure, test and deploy voice and chat agents - Generate speech from text with ElevenLabs voices - Generate music and sound effects - Generate images and video - Review speech history and manage voices ## Example prompts - "Create a customer support voice agent for my bakery and test it." - "Generate a spoken version of this paragraph in a calm voice." - "Make a 30 second upbeat jingle for a podcast intro." - "Generate a sound effect of rain on a tin roof." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http elevenlabs https://api.us.elevenlabs.io/v1/mcp ``` 2. Start Claude Code, type `/mcp`, pick **elevenlabs** and choose **Authenticate**. A browser window opens for the ElevenLabs 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 **ElevenLabs** and paste this URL: ```url https://api.us.elevenlabs.io/v1/mcp ``` 3. Click **Add**, then **Connect**, and sign in when ElevenLabs 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://api.us.elevenlabs.io/v1/mcp` and click **Add**. 3. Click **Connect** and sign in when ElevenLabs 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.us.elevenlabs.io/v1/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to ElevenLabs 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": { "elevenlabs": { "url": "https://api.us.elevenlabs.io/v1/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":"elevenlabs","type":"http","url":"https://api.us.elevenlabs.io/v1/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "elevenlabs": { "type": "http", "url": "https://api.us.elevenlabs.io/v1/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": { "elevenlabs": { "serverUrl": "https://api.us.elevenlabs.io/v1/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 elevenlabs --url https://api.us.elevenlabs.io/v1/mcp codex mcp login elevenlabs ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.elevenlabs] url = "https://api.us.elevenlabs.io/v1/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http elevenlabs https://api.us.elevenlabs.io/v1/mcp ``` Then, inside Gemini CLI, run `/mcp auth elevenlabs` 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": { "elevenlabs": { "type": "http", "url": "https://api.us.elevenlabs.io/v1/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.us.elevenlabs.io/v1/mcp`. ## Details - Server version: 1.0.0 - Last checked: 2026-10-03 (reachable, asks for credentials) - Listed: 2026-10-03 - Updated: 2026-10-04 --- Source: https://mcp.tc/i/elevenlabs (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report