ElevenLabs Plugin

MCP serverMedia

Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use ElevenLabs Plugin

From the project's README

As published by elevenlabs/plugin in README.md.

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/.
SkillDescription
agentsBuild real-time voice AI agents and assistants
dubbingDub audio and video into other languages, preserving the original speakers' voices
musicGenerate instrumental tracks, songs with lyrics, background music, and jingles
setup-api-keyGuide users through configuring an ElevenLabs API key
sound-effectsGenerate sound effects and audio textures from text descriptions
speech-engineAdd real-time voice conversations to your own agent runtime
speech-to-textTranscribe audio to text with Scribe v2
text-to-speechConvert text to natural speech in 70+ languages
voice-changerTransform a recording into a different voice, preserving emotion and timing
voice-isolatorRemove background noise and isolate speech from audio

MCP skills:

SkillDescription
agents-platformCreate, configure, test, and deploy voice agents via the bundled MCP server
creative-studioGenerate speech, images, and video, and transcribe audio via the bundled MCP server

Architect skills:

SkillDescription
agent-simplificationSimplify a complex workflow agent into a leaner architecture, proven equivalent by a test suite
architect-agent-memoryPersist facts an agent should remember, in a durable branch-scoped way
architect-branches-versions-mergeWork with agent branches, versions, drafts, traffic splits, and merges
architect-create-client-toolAdd a client tool that runs in the caller's browser, app, or SDK
architect-create-llm-testCreate a single-turn test that checks what the agent says
architect-create-simulation-testCreate a multi-turn test where a simulated user talks to the agent
architect-create-tool-testCreate a test asserting the agent calls, or avoids, a specific tool
architect-create-webhook-toolGive an agent a new webhook tool that calls an external API
architect-edit-existing-toolChange an existing tool on an agent safely
architect-edit-string-fieldsEdit long text fields like system prompts without clobbering the rest
architect-edit-workflowsBuild or change an agent's workflow graph
architect-explain-test-runsExplain why a test or test run passed or failed
architect-explore-agentMap an agent's current setup before changing it
architect-generate-agentGenerate a new agent from a description
architect-get-agent-ci-greenDrive a red agent test suite to green
architect-llm-selectionChoose the right LLM for an agent
architect-manage-proceduresAdd, edit, rename, and inspect an agent's procedures
architect-migrate-from-competitorMigrate a voice agent from Retell, Vapi, or Bland
architect-migrate-to-proceduresMove a system-prompt-driven agent to a procedure-driven setup
architect-mock-all-toolsMock every tool call so simulation tests are deterministic
architect-post-call-dataConfigure post-call data collection and evaluation criteria
architect-review-live-callsReview recent production conversations and route the findings
architect-schedule-launchStage a change on a branch and hold the merge until go-live
architect-secure-for-productionMake an agent safe, secure, and production-ready
architect-structured-proceduresAuthor structured, deterministic procedures
architect-troubleshoot-tool-errorsDiagnose a misbehaving tool from its exact error
architect-turn-taking-latencyTune turn taking and agent response latency
architect-update-config-safelyChange agent settings with safe partial patches
code-toolsGenerate JavaScript/TypeScript modules for ElevenLabs code tools
fix-agent-qa-ticketFix a QA triage ticket end to end with a verified, branch-scoped fix

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

/plugin marketplace add elevenlabs/plugin
/plugin install elevenlabs@elevenlabs

Or install directly for development: claude --plugin-dir /path/to/plugin

Codex

codex plugin marketplace add elevenlabs/plugin

Then install via /plugins in Codex, or invoke skills with $skill-name.

Skills only (any agent)

npx skills add elevenlabs/skills

Requirements

  • An ElevenLabs account — you'll sign in via OAuth when your agent connects to the MCP server
  • Internet access

Signals

GitHub stars
1
Forks
3
Last commit
Sep 2026
Advanced
Delivery
mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-elevenlabs-mcp
Source
github.com/elevenlabs/plugin
Hosted endpoint
https://api.us.elevenlabs.io/v1/mcp