How to Use the Chatsistant MCP in CrewAI

Deploy an autonomous crew of agents to manage, monitor, and analyze your Chatsistant customer support platform 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 Chatsistant MCP to CrewAI

Create your Vinkius account to connect Chatsistant 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 Chatsistant with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Bot Operations Crew

Assign distinct roles to your CrewAI agents. A 'Monitor' agent can use `list_conversations` to watch for new chats in real time. When it finds one matching certain criteria, it passes the ID to a 'Triage' agent. The Triage agent's job is to use `get_conversation` to analyze the chat's content. If it detects a problem, like a gap in the knowledge base, it can flag it for a 'Technician' agent. The crew works together, sharing context to solve the problem.

Autonomous Knowledge Base Management

This setup lets you build a fully autonomous pipeline. For example, assign a 'Researcher' agent to scan a website for new documentation pages. When it finds one, it passes the content and URL to an 'Updater' agent. The Updater agent’s only job is to use the `add_data_source` tool to push that new content to the correct bot, which it finds using `list_bots`. The entire process runs without any human input, all managed by your CrewAI team.

Multi-Agent System Monitoring with CrewAI

Your crew can perform complex system health checks through a division of labor. One agent's role is to periodically run `list_bots` and `get_bot` to confirm all bots are active and configured correctly. Another agent can simultaneously run `list_webhooks` to ensure all third-party integrations are still firing. If the webhook-checker agent finds a problem, it doesn't solve it; it just passes the finding to a 'Reporter' agent whose only job is to send a detailed alert.

Setup guide

Set up Chatsistant 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 Chatsistant tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The simplest way is to pass your Vinkius MCP URL directly into the `mcps` list when you define an Agent. For more fine-grained control, you can use `MCPServerHTTP` from `crewai.mcp` to filter exactly which tools an agent can access.

Yes, that's a perfect use case for a crew. You would set up one agent with `list_conversations` to scan for new chats. It would then pass the IDs of relevant chats to a second agent that uses `get_conversation` to fetch the full text and analyze it.

That's the core concept of CrewAI. You can have an 'Auditor' agent that uses `list_data_sources` and `list_webhooks` to find issues. It then adds its findings to the shared context for an 'Operator' agent to take corrective action.

No. The MCP server abstracts that away. You provide one Vinkius endpoint URL to your crew. All agents use that single connection, and Vinkius handles the secure communication with the Chatsistant API.

Yes. Your data is only ever in transit through Vinkius's system. All payloads containing conversation details, bot configurations, or webhook info are processed in isolated, single-use sandboxes that are destroyed after your request completes. Vinkius never inspects or retains any of that data.

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