How to Use the ChatGen MCP in CrewAI

Q: Can I build a CrewAI team where one agent finds ChatGen leads and another qualifies them?

Yes, that's a core pattern for CrewAI. Give one agent the listleads tool and a second agent the getleaddetails tool. The first agent's task is to find leads, and it will pass the lead IDs to the second agent for qualification.

Q: Is it possible for a CrewAI agent to update a ChatGen bot based on another agent's analysis?

Absolutely. Create an 'Analyst' agent with access to listconversations and a 'Maintenance' agent with access to updatebot. The Analyst's job is to find poorly performing bots and pass that information to the Maintenance agent, whose job is to apply the fix.

Assemble a crew of AI agents to manage your ChatGen operations. Automate lead monitoring and bot optimization with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatGen MCP to CrewAI

Create your Vinkius account to connect ChatGen 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 ChatGen with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Bot Optimization

This MCP Server lets you build a team of specialized agents to manage your chatbots. Assign roles in CrewAI: an 'Analyst' agent uses `list_conversations` to find underperforming bots, then passes its findings to a 'Technician' agent. The Technician, armed with the `update_bot` tool, applies changes to improve the bot's script. This isn't one agent doing everything; it's a collaborative crew, passing context and tasks through CrewAI's shared memory to keep your bots effective.

Your Autonomous Lead Management Crew

Build a fully automated sales operations team. A 'Scout' agent's only job is to run `list_leads` and find new prospects. When it finds one, it passes the lead ID to an 'Intel' agent. The Intel agent uses `get_lead_details` to enrich the lead's profile. Finally, a 'Dispatcher' agent takes the enriched profile, checks `list_teams` to find the right assignment, and routes the lead. The entire process runs without any human input.

Monitor ChatGen Activity with CrewAI

Set up a security and oversight crew for your ChatGen account. You can have a 'Guard' agent that periodically runs `list_bots` and `list_conversations` to check for anything unusual, like a bot being modified without authorization. If the Guard agent detects an issue, it can delegate the task to an 'Operator' agent. The Operator can then investigate or use the `create_bot` tool to restore a bot from a known-good configuration. It’s an autonomous monitoring and response system.

Setup guide

Set up ChatGen 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 ChatGen tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The simplest way is to pass your Vinkius MCP Server URL directly into the `mcps` list when you define an agent. For more granular control, you can use the `MCPServerHTTP` class to filter exactly which ChatGen tools each agent in your crew can access.

Yes, that's a core pattern for CrewAI. Give one agent the `list_leads` tool and a second agent the `get_lead_details` tool. The first agent's task is to find leads, and it will pass the lead IDs to the second agent for qualification.

Absolutely. Create an 'Analyst' agent with access to `list_conversations` and a 'Maintenance' agent with access to `update_bot`. The Analyst's job is to find poorly performing bots and pass that information to the Maintenance agent, whose job is to apply the fix.

A simple CrewAI setup would be a single agent whose task is to call `list_bots` and `list_conversations`. It can then summarize the activity in its final output or pass the raw data to another agent for deeper analysis.

The server only processes data required by the tools, such as lead contact details and conversation text from your ChatGen account. It operates in a zero-trust environment; every call is authenticated via your token and executed in a separate, sandboxed process that is destroyed immediately after completion.

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