How to Use the Vapi MCP in CrewAI

Q: How do I initiate a test call using Vapi and CrewAI?

You use createphonecall within the agent’s tool set. This allows the crew to automatically dial out, run its process, and get real-time feedback.

Q: Can I see all the tools available to my crew with Vapi and CrewAI?

Yes. The listagenttools function provides a comprehensive view of every operation the entire crew can execute, ensuring no capability is missed.

Run autonomous operations by coordinating specialized teams with CrewAI and Vapi.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vapi MCP to CrewAI

Create your Vinkius account to connect Vapi to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Vapi with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate multi-agent tasks using the MCP Server

CrewAI runs a team, not one agent. You define roles—Agent A researches, Agent B analyzes, Agent C acts. The framework manages this collaboration and shared memory to complete complex operations. It handles sequential or hierarchical execution, moving from research (A) straight into action (C).

Manage specialized assistant personas with CrewAI

You configure the roles using `create_assistant`, defining specific capabilities for each agent in the crew. This ensures Agent A only has access to tools relevant for research, and so on. The system also lets you list all configured assistants via `list_assistants` before starting a new operation.

Handle voice interactions autonomously with CrewAI

A specialized agent can handle the initial contact. By using `create_phone_call`, the crew initiates an outbound call, and other agents monitor the transcript received via `get_call_details` to guide their next action. The overall operation is autonomous—from phone dial to final report.

Setup guide

Set up Vapi MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Vapi tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Vapi Analyst",
    goal="Access and analyze Vapi data via MCP.",
    backstory="Expert analyst with direct Vapi access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Vapi transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Vapi Analyst",
        goal="Access and analyze Vapi data via MCP.",
        backstory="Expert analyst with direct Vapi access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Vapi transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Vapi. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Vapi now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Vapi MCP in CrewAI

You use `create_phone_call` within the agent’s tool set. This allows the crew to automatically dial out, run its process, and get real-time feedback.

Yes. The framework is designed for collaboration, giving specialized agents a shared context so that Agent B knows what Agent A just discovered.

This server handles call metadata, including transcripts and customer details. Because multiple agents are involved, monitoring this PII via `list_calls` is key.

Yes. The `list_agent_tools` function provides a comprehensive view of every operation the entire crew can execute, ensuring no capability is missed.

It's built for that. You define complex workflows where multiple specialized agents take turns using Vapi tools to achieve a final, automated result.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python