ElevenLabs
io.elevenlabsPublished by elevenlabs.ioOfficial publisherv1.0.0Updated Oct 24, 2026
Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
Overview
ElevenLabs hosted MCP server that lets an assistant manage voice agents and generate speech, music, sound effects, images and video.
- What you can do
- Create, update, list, duplicate and delete ElevenLabs voice agents, and inspect widget config, links and knowledge base size, plus estimate LLM usage for agents. Generate text-to-speech audio. Generate music, sound effects, images and video. Transcribe audio and dub or transform voices, per the bundled skills.
- When to use it
- Useful when you want an assistant to build or maintain ElevenLabs voice agents, or to produce speech, music, sound effects, images or video without leaving the chat. It suits Cursor, Claude Code and Codex users already working with ElevenLabs.
- Requirements
- Remote hosted endpoint at api.us.elevenlabs.io; no local install and no API key. An ElevenLabs account signed in through OAuth when the agent connects, plus internet access.
Installation
In SourceWeft
- Open ElevenLabs in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.elevenlabs%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"elevenlabs": {
"type": "http",
"url": "https://api.us.elevenlabs.io/v1/mcp"
}
}
}README
ElevenLabs Plugin
Voice AI capabilities for your coding agent — powered by ElevenLabs. Works with Cursor, Claude Code, and OpenAI Codex.
What's included
Skills
Skills live in three trees:
- skills/general/ — general ElevenLabs product skills, copied from the official elevenlabs/skills repository. Don't edit these here; contribute upstream instead.
- skills/mcp/ — plugin-native skills that teach agents how to drive the bundled ElevenLabs MCP server.
- architect/skills/ — Architect skills: opinionated workflows for building and iterating on ElevenLabs agents, mirrored from the internal Architect plugin. Shared payload examples live in architect/reference/.
MCP skills:
Architect skills:
Architect also ships one command: /thermo-nuclear-agent-triage-burndown, which burns down an agent's whole conversation-triage queue — cluster tickets by root cause, fix each cluster, then comment on and resolve every ticket.
MCP Server
The ElevenLabs hosted MCP server — no local install, no API key. Your agent authenticates with your ElevenLabs account over OAuth and gets access to agent management (create, update, list, duplicate, delete agents; inspect widget config, links, and knowledge base size; estimate LLM usage) and text-to-speech generation. Configured in mcp.json.
Installation
Cursor
Install from the Cursor marketplace, or add this repo as a plugin. When Cursor connects to the MCP server, sign in with your ElevenLabs account to complete the OAuth flow.
Claude Code
Or install directly for development: claude --plugin-dir /path/to/plugin
Codex
Then install via /plugins in Codex, or invoke skills with $skill-name.
Skills only (any agent)
Requirements
- An ElevenLabs account — you'll sign in via OAuth when your agent connects to the MCP server
- Internet access
Source: README.md at commit 1c5f1de
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Elevenlabs integrations
Elevenlabs Mcp
Published by GitHub account runapi-builder
RunAPI MCP server for ElevenLabs that lets an assistant create text-to-speech and text-to-dialogue audio tasks, poll their status, and check pricing.
ElevenLabs Agents
Published by GitHub account mindstone
Manages ElevenLabs Conversational AI voice agents: author agents, review call transcripts, place outbound and batch calls, and edit the knowledge base.
ElevenLabs
Published by GitHub account mindstone
ElevenLabs MCP server that lets an assistant generate speech, music and sound effects, manage voices, dub and transcribe audio.
ElevenLabs
Published by GitHub account mcp-dir
Lets an assistant generate speech, music, sound effects, dubbing and voice management through the ElevenLabs API.
Elevenlabs
com.mcparmory
ElevenLabs MCP server that lets an assistant convert text to speech, transcribe audio, and dub videos with AI voices.