How to Use the Twilio MCP in CrewAI

Q: How does CrewAI handle multi-agent Twilio messaging?

You assign specialized roles. One agent executes sendsms, and another verifies the action by running listmessages. The crew manages the handoff of data between these two distinct, collaborating tasks.

Q: What happens when I need to check account info with Twilio using CrewAI?

A dedicated agent runs getaccountinfo, providing the current status. This data is stored in the shared memory, allowing other agents (e.g., one checking listcallqueues) to reference it immediately.

Q: What type of data does this MCP Server touch regarding privacy?

This server touches call recording details. Calling getrecordingdetails requires a specific Recording SID (RE), giving access to sensitive, stored audio metadata.

Run autonomous Twilio operations with specialized agents using CrewAI framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Twilio MCP to CrewAI

Create your Vinkius account to connect Twilio 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 Twilio with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Communication Workflows

You can assign one agent to handle message sending. This agent uses `send_sms` and reports the result. A second, monitoring agent can then use `list_messages` to verify if the message was actually logged by Twilio. The collaboration between agents makes these operations highly specialized and auditable.

Manage Complex Call Operations

The crew needs a plan for voice communication. Agent A can call `create_voice_call`, while the Moderator agent watches the session status using `list_calls`. If the call must stop, a specialized Action agent calls `cancel_active_call`. This role-based specialization makes complex Twilio operations manageable.

Audit and Retrieve Account Data

Assign an Analyst Agent to run `get_usage_records`. This gathers all billing stats. Another agent can then use the data from `list_api_keys` to check for credential gaps. The shared memory allows agents to pass these account facts—like calling `get_account_info`—to subsequent steps in the operation.

Setup guide

Set up Twilio 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 Twilio tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You assign specialized roles. One agent executes `send_sms`, and another verifies the action by running `list_messages`. The crew manages the handoff of data between these two distinct, collaborating tasks.

Yes. You can set up roles where one agent creates a call with `create_voice_call`, and another handles the termination using `cancel_active_call` if the conversation hits a predefined endpoint.

A dedicated agent runs `get_account_info`, providing the current status. This data is stored in the shared memory, allowing other agents (e.g., one checking `list_call_queues`) to reference it immediately.

It's built for that. By defining a monitor agent and an action agent, you achieve full autonomy—for instance, researching phone numbers with `lookup_phone_number` and then logging the result.

This server touches call recording details. Calling `get_recording_details` requires a specific Recording SID (RE), giving access to sensitive, stored audio metadata.

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