Vapi MCP

Live

OAUTH 2.0

COMMUNICATION

Communication

Connect to Vapi MCP to create and manage AI voice assistants, phone calls, and real-time voice workflows from your AI agent pipelines.

  • Acts as the user: Every tool call runs as the authorizing user. Access and audit trail stay intact.
  • Credentials stay vaulted: AES-256 encrypted, resolved at request time, never stored in LLM context.
  • Scoped before every call: Per-user permissions enforced automatically. 90-day audit trail included.
Vapi MCP
agent · Acme Q3
Run
Create Assistant in Vapi MCP
S
vapimcp_create_assistant
85ms
Vapi MCP agent
Creates a new vapi voice ai assistant with the specified configuration. configure the assistant's llm provider, voice, t.
Sources: Vapi MCP
vapimcpmcp
1 tool call
18:29
Message Claude...

Vapi MCP tools for AI agents

CALL ANY TOOL
12 tools covering create, delete, get.
vapimcp_create_assistant
Create assistant
Creates a new Vapi voice AI assistant with the specified configuration. Configure the assistant's LLM provider, voice, transcription engine, first message, and any tools it should have access to.
Parameters
Name
Type
Required
Description
name
string
Required
Name of the assistant
rationale
string
Required
Always provide a brief explanation of why you are calling this tool
firstMessage
string
Optional
First message the assistant says when a call starts
firstMessageMode
string
Optional
Whether the assistant speaks first or waits for the user
instructions
string
Optional
System instructions for the assistant. Defaults to 'You are a helpful assistant.'
llm
string
Optional
LLM configuration. Defaults to OpenAI gpt-4o.
toolIds
string
Optional
IDs of Vapi tools to attach to this assistant
transcriber
string
Optional
Transcription configuration. Defaults to Deepgram nova-3.
voice
string
Optional
Voice configuration. Defaults to ElevenLabs 'sarah'.
vapimcp_create_call
Create call
vapimcp_create_tool
Create tool
vapimcp_get_assistant
Get assistant
vapimcp_get_call
Get call
vapimcp_get_phone_number
Get phone number
vapimcp_get_tool
Get tool
vapimcp_list_assistants
List assistants
vapimcp_list_calls
List calls
vapimcp_list_phone_numbers
List phone numbers
vapimcp_list_tools
List tools
vapimcp_update_assistant
Update assistant
vapimcp_update_tool
Update tool
Build your Agent
Same auth pattern across every framework.
Python · LlamaIndex
from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="vapimcp")

mcp = MultiServerMCPClient({
"vapimcp": {
"url": "https://mcp.scalekit.com/vapimcp",
"headers": {"Authorization": "Bearer " + token}
}
})
tools = await mcp.get_tools()
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "vapimcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/vapimcp
// Pass: Authorization: Bearer + token
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "vapimcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/vapimcp
// Pass: Authorization: Bearer + token
from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="vapimcp")
# Connect to MCP at https://mcp.scalekit.com/vapimcp
# Pass: Authorization: Bearer + token
Try these prompts
Paste any prompt into your agent to get started.
Get started
Copy the prompt
Copied
Updates an existing Vapi tool’s configuration?
Copy the prompt
Copied
Lists all Vapi tools configured in the account?
Advanced
Copy the prompt
Copied
Retrieves the full configuration of a specific Vapi tool by ID, including its type (SMS, transfer call, function, or API?
Copy the prompt
Copied
Creates a new Vapi tool that can be attached to assistants?
SEE HOW AUTH WORKS
User authorises once. Every agent call after uses their token with scope enforcement.
1
Authorize
Your user connects
Vapi MCP
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
Vapi MCP
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
Vapi MCP
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
Vapi MCP
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 connectors.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
Support and Ops Teams
Support triage agent
Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
Test other agents
See the same per-user auth pattern across other connectors.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
SUPPORT
Support triage agent
Classify new Zendesk tickets, search the Notion knowledge base for an answer, and route what it cannot resolve to Slack.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
One connector today. Ten 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 Vapi as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Vapi OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Vapi?
Yes. Pass a tool name filter to listScopedTools so the messaging agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Vapi.

What happens when a user revokes Vapi 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 modify voice assistants and place calls?
Yes, within the authorizing user's Vapi account. Assistant edits, call placement, and phone number changes run under that user's credential. Filter to read-only tools if you want reporting without call spend.

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"": {
""vapimcp"": {
""url"": ""https://mcp.scalekit.com/vapimcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.vapimcp]
url = ""https://mcp.scalekit.com/vapimcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""vapimcp"": {
""url"": ""https://mcp.scalekit.com/vapimcp"",
""type"": ""http""
}
}
}