How to Use the ChatFly MCP in CrewAI

Q: Can a CrewAI team manage multiple ChatFly instances simultaneously?

Yes. A coordinator agent can use listbots to get the list of active bots, then delegate individual maintenance tasks to different specialist agents.

Q: Where does my customer chat data go when CrewAI runs tests on this MCP Server?

All interactions triggered by the chat tool go directly to the sandboxed API on Vinkius and are never stored in CrewAI's memory logs. This ensures that sensitive customer inquiries and bot configurations remain completely private.

Deploy a crew of autonomous agents that build, monitor, and train ChatFly support bots collaboratively using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatFly MCP to CrewAI

Create your Vinkius account to connect ChatFly 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 ChatFly with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinated bot creation

Using the `create_bot` tool with this MCP Server lets your specialized agents collaborate to initialize customer support bots dynamically. They share memory to ensure the welcome message matches the brand guidelines. You get a fully coordinated setup process where agents check each other's work before going live.

Automatic knowledge base audits

Your researcher agent can call the `list_data_sources` tool to audit what files your support bots are currently using. If it finds gaps, it passes the new files to the database agent, which executes `upload_data_source` to refresh the knowledge base. This keeps your support bots updated without human developers in the loop.

Automated QA via an MCP Server

Your QA crew can initiate test conversations with the `chat` tool to evaluate the quality of live agent responses. If the Critic Agent finds errors, it instructs a Coordinator Agent to call `update_bot` with corrected guidelines. This creates a continuous feedback loop that polishes your customer-facing responses autonomously.

Setup guide

Set up ChatFly 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 ChatFly tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can pass the MCP Server URL directly to the agent's setup. This allows you to give the `chat` tool to your customer-facing agent while restricting `update_bot` to your admin agent.

Yes. A coordinator agent can use `list_bots` to get the list of active bots, then delegate individual maintenance tasks to different specialist agents.

CrewAI agents use shared memory to pass bot details retrieved from `get_bot` to other team members who might need to run test conversations.

The framework supports stdio, SSE, and HTTP transports out of the box. For most cloud setups, connecting your agents to the Vinkius hosted endpoint via HTTP is the easiest way to expose the tools.

All interactions triggered by the `chat` tool go directly to the sandboxed API on Vinkius and are never stored in CrewAI's memory logs. This ensures that sensitive customer inquiries and bot configurations remain completely private.

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