How to Use the Vibrato MCP in CrewAI

Q: How does Vibrato integrate with my CrewAI setup?

You expose the tools via MCPServerHTTP and pass them to your agents. This lets one of your specialized crew members automatically call the phone server when needed.

Q: Can I use Vibrato for monitoring calls within CrewAI?

Yes, the monitor agent can run listcalls across all active and finished sessions. This provides a central view of every action taken by your autonomous crew.

Q: What if my CrewAI needs to initiate a call from a template?

Just assign the task using the agent that calls createcallfromtemplate. The script handles the complexity, and the rest of the team processes the outcome.

Q: Is Vibrato good for complex phone sequences in CrewAI?

It's perfect. You can sequence actions: Agent A calls createcall, waits 5 minutes, then Agent B checks status using getcallstatus.

Build Autonomous Operations: Multi-Agent Phone Calling with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vibrato MCP to CrewAI

Create your Vinkius account to connect Vibrato 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 Vibrato with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Launch Calls Using Templates

The `create_call_from_template` tool lets your crew of agents act autonomously. One agent can be assigned the role of calling, using a pre-defined script like 'Negotiate Bill.' This is ideal for setting up autonomous operations that require immediate action based on shared knowledge.

Monitor and List All Calls

You can assign an agent the task of monitoring outcomes using `list_calls`. This agent reports the full history of AI interactions to the rest of the crew. Another specialized agent can use `get_call_status` to check if a call is stuck, allowing the moderator agent to take action.

Start Calls with Custom Prompts

If the situation requires something unique, the crew uses `create_call`, passing specific prompts and phone numbers. This allows for dynamic escalation when standard templates fail. The role-based specialization means one agent focuses solely on calling while another handles the data payload.

Setup guide

Set up Vibrato 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 Vibrato tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Vibrato 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="Vibrato Analyst",
        goal="Access and analyze Vibrato data via MCP.",
        backstory="Expert analyst with direct Vibrato access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Vibrato 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 Vibrato. 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 Vibrato 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 Vibrato MCP in CrewAI

You expose the tools via `MCPServerHTTP` and pass them to your agents. This lets one of your specialized crew members automatically call the phone server when needed.

Yes, the monitor agent can run `list_calls` across all active and finished sessions. This provides a central view of every action taken by your autonomous crew.

Just assign the task using the agent that calls `create_call_from_template`. The script handles the complexity, and the rest of the team processes the outcome.

It's perfect. You can sequence actions: Agent A calls `create_call`, waits 5 minutes, then Agent B checks status using `get_call_status`.

The server manages the phone numbers and the detailed metadata about each interaction. This allows your crew to build complex decision trees based on historical results.

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

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript