Twelvelabs MCP server

Read from the package source without running it. The installed server may list more.

• el_create_webhookwrite action

  Create a new ElevenLabs webhook. The most common event to subscribe to is "post_call_transcription" — ElevenLabs will POST to your URL after every conversation ends, including the transcript, data_collection results, and evaluation criteria. Returns the webhook_id and signing secret (save the secret — it won't be shown again).

• el_delete_webhookwrite action

  Permanently delete a webhook. ElevenLabs will stop sending events to its endpoint. This cannot be undone.

• el_list_webhooks

  List all configured webhooks in your ElevenLabs account. Returns webhook IDs, names, endpoint URLs, subscribed event types, and active/inactive status.

• el_update_webhookwrite action

  Update an existing webhook's URL, display name, subscribed events, or status (active/inactive). Supply only the fields you want to change.

• twelvelabs_add_kb_text

  Add a plain text document to the ElevenLabs knowledge base. After adding, attach it to an agent by updating the agent's knowledge_base config with the returned document ID. Args: - name: Display name for the document - text: The full text content to store Returns: The new document's ID and name. Note: This creates the document in your account-level knowledge base but does NOT automatically attach

• twelvelabs_add_kb_url

  Add a web page to the knowledge base by URL. ElevenLabs will crawl the URL and extract the text content. Args: - name: Display name for the document - url: The URL to crawl Returns: The new document's ID. Note: This creates the document in your account-level knowledge base but does NOT automatically attach it to any agent. Use twelvelabs_get_agent to check an agent's current KB attachments.

• twelvelabs_delete_kb_docwrite action

  ⚠️ IRREVERSIBLE. Permanently deletes a knowledge base document. Confirm with the user before calling. The document will also be detached from any agents that reference it. Args: - doc_id: The document ID to delete

• twelvelabs_get_agent

  Get the FULL configuration of an ElevenLabs agent, including fields the official ElevenLabs MCP connector does not expose: - Complete system prompt text - LLM model (e.g., gpt-4.1-nano, claude-3-5-haiku) - Temperature setting - All knowledge base document references - Voice ID and TTS settings (stability, similarity_boost) - Language configuration - Webhook URL (if configured) - First message Args

• twelvelabs_get_agent_prompt

  Get the complete, untruncated system prompt for an ElevenLabs agent. Use this when you need to read, review, or edit the full prompt text. twelvelabs_get_agent truncates the prompt to 500 chars for readability — this tool returns the entire thing. Args: - agent_id: The agent ID

• twelvelabs_get_agent_webhook

  Get the post-call webhook URL configured for an agent. Args: - agent_id: The agent ID

• twelvelabs_get_conversation

  Get the complete transcript and post-call analysis for a conversation. Returns two things: 1. The full turn-by-turn transcript (what the agent and user actually said) 2. The analysis: data_collection fields (scores, email, role, recommendation) and evaluation_criteria results (booleans like interview_completed) This is your primary tool for debugging: if scores are wrong, feedback is missing, or t

• twelvelabs_get_kb_doc

  Get the full content of a knowledge base document, including its extracted text. Args: - doc_id: The document ID (from twelvelabs_list_kb_docs) Returns: Document metadata plus the full extracted text content.

• twelvelabs_list_agent_conversations

  List recent conversations for a specific ElevenLabs agent. Useful for finding conversation IDs to pass to twelvelabs_get_conversation for full transcripts and data collection analysis. Args: - agent_id: The agent ID - limit: Number of conversations to return (1–100, default 20) Returns: List of conversations with ID, status, duration, and timestamp. Tip: This is equivalent to twelvelabs_list_conve

• twelvelabs_list_agents

  List all Conversational AI agents in your ElevenLabs account. Returns each agent's ID, name, and creation timestamp. Use this to find agent IDs before calling twelvelabs_get_agent for full details. Returns: Array of { agent_id, name, created_at_unix_secs }

• twelvelabs_list_conversations

  List recent conversations across all agents in your account. To filter by agent, use twelvelabs_list_agent_conversations instead. Args: - limit: Number of conversations to return (1–100, default 20) - agent_id: Optional — filter to a specific agent Returns: List of conversations with ID, status, duration, and agent ID. Tip: To filter by agent, either pass agent_id here or use twelvelabs_list_agent

• twelvelabs_list_kb_docs

  List all documents in your ElevenLabs knowledge base. Note: KB documents exist at the account level, not per-agent. They are referenced from agents via the agent's knowledge_base config array. Use twelvelabs_get_agent to see which docs a specific agent has attached. Returns: Each doc's ID, name, type (file/url), size, and creation date.

• twelvelabs_list_voices

  List available voices in your ElevenLabs account. Returns voice IDs, names, categories, and labels. Use the voice_id values with twelvelabs_update_agent_settings. Args: - search: Optional text filter applied to voice names

• twelvelabs_set_agent_webhook

  ⚠️ This modifies a LIVE agent's webhook configuration. Confirm with the user before calling. Set or update the post-call webhook URL for an ElevenLabs agent. ElevenLabs will POST a payload to this URL after each conversation ends, containing the transcript and data collection results. Pass an empty string to remove the webhook. Args: - agent_id: The agent ID - url: The webhook URL (empty string to

• twelvelabs_update_agent_promptwrite action

  ⚠️ This modifies a LIVE agent's configuration. Confirm with the user before calling. Replace the system prompt and/or first message for an ElevenLabs agent. This uses a PATCH request, so any fields you omit are left unchanged. Only touches prompt text and first_message — does not affect voice, LLM model, or other settings. Args: - agent_id: The agent ID - prompt: New system prompt text (omit to le

• twelvelabs_update_agent_settingswrite action

  ⚠️ This modifies a LIVE agent's configuration. Confirm with the user before calling. Update voice, LLM, temperature, or language settings for an agent. All parameters are optional — only provide the ones you want to change. Omitted values are left unchanged (PATCH semantics). Args: - agent_id: The agent ID - temperature: LLM temperature 0.0–1.0 (higher = more varied responses) - voice_id: ElevenLa

• Code scan17 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 18 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

83/100

higher than 70% of 1,337 Media servers

Tools

20

the typical Media server has 7

Tools that change things

30%

typical: 4%. Fewer write tools means less an agent can break

Twelvelabs: common questions

Is Twelvelabs MCP server safe?

Mostly: it is graded B (83/100). Read the Twelvelabs safety report

How do I install Twelvelabs?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Twelvelabs need an API key?

Yes. The registry entry asks for ELEVENLABS_API_KEY.

Is Twelvelabs maintained?

The last commit was 56 days ago (2026-09-09). The latest release is v1.0.1.

What can I use instead of Twelvelabs?

Servers from other publishers that do the same job: SuperCMO MCP server, Sapiens Sintéticos MCP server and ElevenLabs MCP server.

How does Twelvelabs compare with other Media MCP servers?

safety score 83/100 (higher than 70% of 1,337 Media servers); tools 20 (the typical Media server has 7); tools that change things 30% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.