ElevenLabs MCP server for AI agents

Live

API KEY

VOICE AI

AI

ElevenLabs gives your agent voice AI: generate speech and multi-speaker dialogue, design and manage voices, run conversational agents with knowledge bases and phone calls, and work with dubbing, Studio, and pronunciation dictionaries.

  • Per-user credentials: each call uses the actual user's API key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
ElevenLabs
agent · Acme Q3
Run
How many conversations did the support agent handle yesterday, and how many failed?
S
elevenlabs_list_conversations
109ms
Voice ops agent
The support agent handled 86 conversations yesterday. 7 of them were marked unsuccessful.
Sources: 86 conversations
elevenlabs
86 conversations
18:29
Message Claude...

Tools your voice ops agent reaches for on ElevenLabs, scoped per user.

CALL ANY TOOL
119 tools for voice AI in ElevenLabs: generate speech and dialogue, design, remix, and manage voices, build and test conversational agents, search conversations, run batch and outbound calls, and manage knowledge bases, dubbing, and Studio projects.
elevenlabs_add_pronunciation_rules
Add pronunciation rules
Add rules to the pronunciation dictionary. Returns an object with id, version_id, version_rules_num. Use elevenlabs_list_pronunciation_dictionaries to find the id.
Parameters
Name
Type
Required
Description
pronunciation_dictionary_id
string
Required
The id of the pronunciation dictionary.
rules
array
Required
List of pronunciation rules. Rule can be either: an alias rule: {'string_to_replace': 'a', 'type': 'alias', 'alias': 'b', } or a phoneme rule: {'string_to_replace': 'a', 'type': 'phoneme', 'phoneme': 'b', 'alphabet': 'ipa' }. Example: [{"string_to_replace": "ElevenLabs", "type": "alias", "alias": "eleven labs"}].
elevenlabs_assign_conversation_tags
Assign conversation tags
elevenlabs_cancel_batch_call
Call cancel batch
elevenlabs_create_agent
Create agent
elevenlabs_create_conversation_tag
Create conversation tag
elevenlabs_create_mcp_server
Create mcp server
elevenlabs_delete_agent
Delete agent
elevenlabs_delete_agent_tool
Delete agent tool
elevenlabs_delete_history_item
Delete history item
elevenlabs_delete_phone_number
Delete phone number
elevenlabs_get_agent
Get agent
elevenlabs_get_agents_settings
Get agents settings
elevenlabs_get_default_voice_settings
Get default voice settings
elevenlabs_get_mcp_server
Get mcp server
elevenlabs_get_subscription
Get subscription
elevenlabs_list_agent_environment_variables
List agent environment variables
elevenlabs_list_agent_tools
List agent tools
elevenlabs_list_knowledge_base_document_agents
List knowledge base document agents
elevenlabs_list_music_finetunes
List music finetunes
elevenlabs_query_agent_knowledge_base
Query agent knowledge base
elevenlabs_refresh_knowledge_base_url_document
Refresh knowledge base url document
elevenlabs_remove_pronunciation_rules
Remove pronunciation rules
elevenlabs_run_agent_tests
Run agent tests
elevenlabs_search_conversation_messages
Search conversation messages
elevenlabs_set_pronunciation_rules
Set pronunciation rules
elevenlabs_start_sip_trunk_outbound_call
Call start sip trunk outbound
elevenlabs_submit_conversation_feedback
Submit conversation feedback
elevenlabs_update_agent
Update agent
elevenlabs_update_agents_settings
Update agents settings
elevenlabs_update_mcp_server
Update mcp server

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// ElevenLabs tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["elevenlabs"], toolNames: [
    "elevenlabs_list_voices",
    "elevenlabs_text_to_speech",
    "elevenlabs_text_to_dialogue"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Turn this paragraph into speech with our narrator voice" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["elevenlabs"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Turn this paragraph into speech with our narrator voice" }],
  tools,
});

// Execute the tool call with the user's vaulted ElevenLabs API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["elevenlabs"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Turn this paragraph into speech with our narrator voice" }],
  tools,
});

// Tool call runs with the user's vaulted ElevenLabs API key
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["elevenlabs"] }, pageSize: 100,
});

const agent = new Agent({
  name: "voice_ops_agent",
  model: "gemini-2.5-pro",
  instruction: "ElevenLabs tools scoped to this user",
  tools,
});

await agent.run("Turn this paragraph into speech with our narrator voice");
Try these prompts
Copy any prompt into your agent. Each maps directly to a ElevenLabs tool. Click to copy, paste into your agent, done.
Speech and voices
Copy the prompt
Copied
Turn this paragraph into speech with our narrator voice.
Copy the prompt
Copied
Generate a 2-speaker dialogue from this interview script.
Copy the prompt
Copied
Design a warm, calm voice for our onboarding videos.
Agents
Copy the prompt
Copied
List our agents and show the support agent's config.
Copy the prompt
Copied
Search last week's conversations for mentions of refunds.
Copy the prompt
Copied
Run the selected tests on the booking agent.
Calls and content
Copy the prompt
Copied
Start a batch call to these 50 customers with the reminder agent.
Copy the prompt
Copied
Add our help center URL to the agent's knowledge base.
Copy the prompt
Copied
Show the status of the Spanish dubbing project.
SEE HOW AUTH WORKS
Each user connects their own ElevenLabs API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
ElevenLabs
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
ElevenLabs
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
ElevenLabs
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
ElevenLabs
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other AI and media connectors.
Support and Ops Teams
Support ticket automation agent
Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
Test other agents
See the same per-user auth pattern across other AI and media connectors.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared ElevenLabs API key looks fine in a demo. In production every speech generation and agent change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
ElevenLabs today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access ElevenLabs as the user or through a shared API key?
As the user. Each user connects their own ElevenLabs API key once, and Scalekit sends it with every call. Audit logs attribute every speech generation and agent change to that user, not a shared service account.
Where is the ElevenLabs API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in ElevenLabs?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example speech generation and conversation search without elevenlabs_delete_agent or elevenlabs_delete_voice. Scalekit also enforces scope checks before every API call.
What happens when a user revokes ElevenLabs access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent place phone calls through ElevenLabs agents?
Yes, if you expose those tools. elevenlabs_start_twilio_outbound_call and elevenlabs_start_sip_trunk_outbound_call start an outbound call with an agent, and elevenlabs_create_batch_call schedules calls for many recipients. elevenlabs_cancel_batch_call stops a running batch.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""elevenlabs"": {
""url"": ""https://mcp.scalekit.com/elevenlabs"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.elevenlabs]
url = ""https://mcp.scalekit.com/elevenlabs""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""elevenlabs"": {
""url"": ""https://mcp.scalekit.com/elevenlabs"",
""type"": ""http""
}
}
}