About io.github.micro-JAY/twelvelabs-mcp-server
io.github.micro-JAY/twelvelabs-mcp-server is an MCP server published by micro-JAY in the Developer Tools category: mCP server for ElevenLabs Conversational AI — manage agents, knowledge base, conversations, voices.
Recent commit activity is the strongest signal that reported issues will get attention.
Install
claude mcp add io-github-micro-jay-twelvelabs-mcp-server -- npx -y twelvelabs-mcp-servernpx -y twelvelabs-mcp-serverThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
twelvelabs_get_agentFull config: LLM model, voice, KB docs, webhook, prompt preview
Parameters not published.
twelvelabs_get_agent_promptFull untruncated system prompt text
Parameters not published.
twelvelabs_get_agent_webhookCurrent webhook URL
Parameters not published.
twelvelabs_list_agent_conversationsRecent conversations for one agent
Parameters not published.
twelvelabs_list_agentsList all agents in your account
Parameters not published.
twelvelabs_set_agent_webhookSet or remove webhook URL
Parameters not published.
twelvelabs_update_agent_conversation_capabilitiesEnable chat file uploads and set the maximum-duration message
Parameters not published.
twelvelabs_update_agent_promptReplace system prompt and/or first message
Parameters not published.
twelvelabs_update_agent_settingsChange temperature, voice, TTS settings, language
Parameters not published.
Ask AI
Ask AI about io.github.micro-JAY/twelvelabs-mcp-server
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
5 checks have not been run yet.
README
TwelveLabs MCP Server
This project is not affiliated with TwelveLabs (the video understanding platform). It is an MCP server for the ElevenLabs Conversational AI API — voice agents, knowledge bases, conversations, and TTS. The name "TwelveLabs" is the project codename only.
An enhanced MCP (Model Context Protocol) server that gives Claude direct access to the ElevenLabs Conversational AI API -- including capabilities the official ElevenLabs MCP connector doesn't expose.
What this covers
- Agents -- list, get full config (including LLM model + temperature), update prompt/settings, manage webhooks
- Knowledge Base -- list, read full content, add text/URL docs, delete docs
- Conversations -- list, get full transcript + data_collection analysis
- Voices -- list and search available voices
Prerequisites
- Node.js >= 18
- ElevenLabs API key -- get one at elevenlabs.io
Quick Start
Option A: npx (no clone needed)
ELEVENLABS_API_KEY=your-key npx twelvelabs-mcp-server
Option B: Clone and build
git clone https://github.com/micro-JAY/twelvelabs-mcp-server.git
cd twelvelabs-mcp-server
npm install --include=dev
npm run build
Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"twelvelabs": {
"command": "node",
"args": ["/path/to/twelvelabs-mcp-server/dist/index.js"],
"env": {
"ELEVENLABS_API_KEY": "your-api-key-here"
}
}
}
}
Then restart Claude Desktop. You should see "twelvelabs" in the available tools panel.
Use it
In any Claude conversation:
"List my agents" "Get the full config for agent_1001kjbh14xce5kbreh55ydf4rae" "Show me the last 10 conversations for that agent" "Get the transcript and analysis for conversation_xyz"
Tool Reference
Agent Tools
| Tool | What it does |
|---|---|
twelvelabs_list_agents |
List all agents in your account |
twelvelabs_get_agent |
Full config: LLM model, voice, KB docs, webhook, prompt preview |
twelvelabs_get_agent_prompt |
Full untruncated system prompt text |
twelvelabs_update_agent_prompt |
Replace system prompt and/or first message |
twelvelabs_update_agent_settings |
Change temperature, voice, TTS settings, language |
twelvelabs_list_agent_conversations |
Recent conversations for one agent |
twelvelabs_get_agent_webhook |
Current webhook URL |
twelvelabs_set_agent_webhook |
Set or remove webhook URL |
Knowledge Base Tools
| Tool | What it does |
|---|---|
twelvelabs_list_kb_docs |
All KB docs with size and creation date |
twelvelabs_get_kb_doc |
Full extracted text content of a doc |
twelvelabs_add_kb_text |
Add a plain text document |
twelvelabs_add_kb_url |
Add a web page by URL |
twelvelabs_delete_kb_doc |
Permanently delete a doc |
Conversation Tools
| Tool | What it does |
|---|---|
twelvelabs_list_conversations |
Recent conversations (optionally filtered by agent) |
twelvelabs_get_conversation |
Full transcript + data_collection + evaluation_criteria |
Voice Tools
| Tool | What it does |
|---|---|
twelvelabs_list_voices |
Browse available voices with IDs and labels |
Security
- Input validation -- all tool parameters are validated with Zod schemas before reaching the API
- HTTPS enforcement -- webhook URLs are validated to use HTTPS only
- Path traversal protection -- document and agent IDs are sanitized to prevent path traversal
- Error sanitization -- internal errors are caught and returned as safe MCP error responses; raw stack traces are never exposed to the client
Development
npm run dev # watch mode with tsx -- auto-reloads on file changes
npm run build # compile to dist/
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feat/my-feature) - Commit your changes (
git commit -m 'feat: add my feature') - Push to the branch (
git push origin feat/my-feature) - Open a Pull Request
License
MIT -- see LICENSE for details.
Architecture Note
All tools share a single Axios client instance (src/client.ts) initialised from
ELEVENLABS_API_KEY at startup. Tool implementations live in src/tools/ -- one
file per domain -- and are registered onto the McpServer in src/index.ts. The
server communicates over stdio transport (stdin/stdout), which is why all debug
logging uses console.error (stderr), not console.log.
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.