How to Use the CallFire MCP in CrewAI

Deploy autonomous CrewAI multi-agent teams that monitor and analyze CallFire communications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallFire MCP to CrewAI

Create your Vinkius account to connect CallFire 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 CallFire with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Telephony Logs with CallFire MCP Server

The `list_calls` tool extracts bulk historical records of your outbound dialing activity. CrewAI assigns this extraction task to a dedicated researcher agent that pulls the data into shared memory. A secondary analyst agent then reviews the call durations and costs to identify inefficient campaigns. Running `list_sent_sms` gives your crew a complete view of recent text broadcasts. The agents can cross-reference delivery timestamps against customer response rates. They build a complete performance report without human intervention.

Execute Multi-Agent Outbound Campaigns

The `send_sms` tool allows your action-oriented agents to dispatch texts based on the research team's findings. If the monitoring agent detects a server outage, the responder agent immediately drafts and fires off an alert to the engineering team. This specialization keeps logic cleanly separated. Triggering `send_voice_call` physically rings the on-call engineer when a text goes ignored. Escalation protocols often require escalating mediums. The crew maintains context across the entire incident, knowing exactly who was contacted and through which channel.

Manage Audio Files and Account Limits

The `list_campaign_sounds` tool retrieves the unique identifiers for your pre-recorded voice broadcasts. Your campaign manager agent uses this list to verify the correct audio file exists before scheduling a massive robocall. This prevents silent calls and wasted account credits. Executing `get_account_info` allows a financial overseer agent to check your balance. Monitoring those available credits is a continuous background task. If funds drop below a critical threshold, the crew can pause all outbound activity and alert the billing department.

Setup guide

Set up CallFire 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 CallFire tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install the core framework with the tools extra using pip. You pass your Vinkius HTTP endpoint directly into the `mcps` array on your Agent definition. The system automatically registers all ten telephony functions.

You should absolutely limit agent capabilities based on their role. Use the `MCPServerHTTP` class and apply a `tool_filter`. Give your analyst agent access to message details while restricting broadcast abilities exclusively to your communications agent.

The framework handles context sharing natively. When your researcher pulls data using the call details operation, that specific duration and cost information enters the crew's shared memory. Subsequent agents read that memory to inform their next actions.

We recommend standard HTTP polling or SSE for Python environments. Vinkius MCP Server endpoints handle the auth and routing automatically. You just provide the URL and the single endpoint token.

Your communication records are completely walled off inside a V8 Isolate. The system processes your requests in an ephemeral sandbox that holds zero state. Nobody, including our infrastructure team, can access your raw telephony payloads.

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