How to Use the Callpicker MCP in CrewAI

Q: How can I build a CrewAI team to analyze call performance with the Callpicker MCP?

Assign one agent the task of fetching data with getcdrreport. Pass that data to a second agent to perform analysis. A third agent can then summarize the findings and report back. It's a classic research-analyze-report pattern.

Q: Can a CrewAI agent use Callpicker to automatically dial a new lead?

Yes. You can have one agent identify a lead from listcalllogs and then delegate the makecall task to a specialized "dialer" agent in the same crew. This is a perfect use case for role-based agents.

Q: Is it possible for a crew to list all virtual numbers and check activity?

Definitely. An agent can use listvirtualnumbers to get the full list. You can then have another agent in the crew loop through them to check their status or recent call activity using other Callpicker tools.

Deploy an autonomous crew to manage your phone system. CrewAI agents use Callpicker to monitor calls, analyze performance, and take action.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to CrewAI

Create your Vinkius account to connect Callpicker 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 Callpicker with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Call Monitoring Crew

Don't build a monolith. Create a "Monitoring Agent" whose only job is to run `list_call_logs` every minute. When it finds a new call, it passes the call ID to a specialized "Details Agent" on the same crew. The "Details Agent" then uses `get_call_details` and `get_recording_url` to gather all available information. It adds this structured data to the crew's shared memory for other agents to use. This MCP enables that clean separation of concerns that makes CrewAI so effective.

Qualify Leads with a CrewAI Team

An "Analyst Agent" can pull reports with `get_cdr_report` to identify calls from specific marketing campaigns, looking for patterns like calls from a certain virtual number. It's a dedicated researcher. When it finds a hot lead, it tasks a "Sales Dialer Agent" to use the `make_call` tool to connect a sales rep. The whole process, from detection to action, is handled autonomously by the crew. This MCP Server gives your agents the exact telephony tools they need.

Your Autonomous PBX Maintenance Crew

Designate a "System Check Agent" to periodically run `get_pbx_system_status`. It does nothing else. This makes your setup clean, predictable, and easy to debug. If that agent fails, you know exactly where the problem is. If the status check fails, it can trigger a hierarchical task for an "Escalation Agent". That agent could then try to gather more info using other tools or send a high-priority alert to an admin. You're building a digital NOC team.

Setup guide

Set up Callpicker 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 Callpicker tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Assign one agent the task of fetching data with `get_cdr_report`. Pass that data to a second agent to perform analysis. A third agent can then summarize the findings and report back. It's a classic research-analyze-report pattern.

Yes. You can have one agent identify a lead from `list_call_logs` and then delegate the `make_call` task to a specialized "dialer" agent in the same crew. This is a perfect use case for role-based agents.

It's straightforward. Just pass the Vinkius MCP URL for Callpicker into the `mcps` parameter when you define your Agent in CrewAI. The framework handles the tool discovery and integration.

Definitely. An agent can use `list_virtual_numbers` to get the full list. You can then have another agent in the crew loop through them to check their status or recent call activity using other Callpicker tools.

Access is controlled by your Vinkius API token. Only agents within your crew that possess the token can use the `get_recording_url` tool. The connection is always encrypted, and the Callpicker MCP server doesn't permanently store your call data or recordings.

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