How to Use the Kavkom MCP in CrewAI

Q: How do I pass the Kavkom MCP Server to CrewAI?

Provide the Vinkius endpoint URL in the mcps array when defining your agent. The framework connects and registers the available tools on boot.

Q: Can a CrewAI agent analyze Kavkom call logs automatically?

Yes. Give an agent access to listcalls. It will fetch the records, read the metadata, and summarize the daily phone activity without human prompting.

Q: Does CrewAI support filtering Kavkom tools?

It does. You initialize MCPServerHTTP and use the toolfilter parameter. This ensures a read-only agent cannot execute state-changing tools like creating contacts.

Equip your CrewAI agent teams with Kavkom cloud telephony to automate customer support operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kavkom MCP to CrewAI

Create your Vinkius account to connect Kavkom 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 Kavkom with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze call logs autonomously

`list_calls` and `get_call_details` feed raw call history to your specialized agents. You assign these tools to a researcher agent, which pulls the logs for the last 24 hours. That agent hands the data off to an analyst agent to find missed calls. CrewAI thrives on this kind of role-based execution. The agents share memory, so the analyst knows exactly what the researcher found. Nobody writes boilerplate code to pass JSON between functions.

Enable two-way text messaging

`send_sms_message` and `list_sms_history` give your CrewAI agents two-way text capabilities. A responder agent can read the history of a specific phone number, draft a context-aware reply, and send it. You build autonomous operations that handle low-level customer queries without waking up a human. Setup is dead simple. You pass the Vinkius URL directly into the `mcps` array on your agent definition. The framework handles the transport negotiation and exposes the tools automatically.

Route complex issues to humans

`list_team_members` and `list_crm_contacts` let your agents route complex issues to actual employees. If an autonomous agent hits a wall, it pulls the active user list and finds the right manager. It then creates a contact record for the angry customer and flags it for review. Sometimes you don't want an agent accessing every single tool. You can use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. This restricts a specific agent to only reading contacts, preventing it from accidentally sending a text message.

Setup guide

Set up Kavkom 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 Kavkom tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Provide the Vinkius endpoint URL in the `mcps` array when defining your agent. The framework connects and registers the available tools on boot.

Yes. Give an agent access to `list_calls`. It will fetch the records, read the metadata, and summarize the daily phone activity without human prompting.

It does. You initialize `MCPServerHTTP` and use the `tool_filter` parameter. This ensures a read-only agent cannot execute state-changing tools like creating contacts.

Yes. The agents operate with shared memory. One can fetch call details while another drafts an SMS response based on that exact data.

We enforce a zero-trust architecture. Your agent authenticates with a single endpoint token, and the temporary container purges all contact data immediately after the API returns.

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