How to Use the Crisp MCP in AutoGen

Q: How do I register Crisp tools with AutoGen?

Install autogen-extmcp and use the MCP server tools helper with your Vinkius Crisp URL. Pass the tools list to your AssistantAgent constructor to give them access to Crisp.

Q: Can I restrict certain agents from sending messages?

Yes, you can omit sendmessage from the tool list passed to certain AutoGen agents. This keeps your writer agents sandboxed to read-only actions while leaving execution to a supervisor agent.

Enable AutoGen agents to debate support issues and coordinate real-time replies on your Crisp live chat.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crisp MCP to AutoGen

Create your Vinkius account to connect Crisp to AutoGen 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 Crisp with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Crisp support replies via AutoGen agents

The `send_message` tool allows your AutoGen agent group to post finalized support replies back to Crisp. You set up a multi-agent workflow where a writer agent drafts the message and a reviewer agent approves it. This consensus-driven approach prevents incorrect information from reaching your Crisp chat. No message is sent via `send_message` until both AutoGen agents agree the draft is accurate.

Analyze complex issues with multi-agent debate

The `get_messages` tool pulls the complete history of an unresolved Crisp conversation for your AutoGen agents to analyze. This Crisp MCP Server tool provides the raw text that your agents debate to find the root cause of a bug. One AutoGen agent analyzes the technical details while another looks up user history using `get_visitor_profile`. They exchange findings in a structured conversation loop to form a unified troubleshooting plan for the Crisp visitor.

Automate queue triage with consensus

The `list_conversations` tool retrieves the active Crisp inbox queue so your AutoGen coordinator agent can assign tasks. This Crisp MCP tool feeds the live list to your agent cluster for immediate categorization. The AutoGen agents debate which Crisp tickets require urgent human attention and which can be handled automatically. Your support triage remains consistent because it relies on cooperative decision-making.

Setup guide

Set up Crisp MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Crisp tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Crisp_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Crisp data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Crisp_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Crisp data")
    print(result.messages[-1].content)

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 Crisp. 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 Crisp 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 Crisp MCP in AutoGen

Install `autogen-ext[mcp]` and use the MCP server tools helper with your Vinkius Crisp URL. Pass the tools list to your `AssistantAgent` constructor to give them access to Crisp.

Yes, you can share the Crisp MCP tool list across your AutoGen group. One agent can use `get_visitor_profile` while another uses `get_messages` to collaborate on a ticket.

The agents use structured LLM function calling to select Crisp tools based on the current debate. If an agent needs context, it automatically invokes `get_conversation` to inspect the chat.

Yes, you can omit `send_message` from the tool list passed to certain AutoGen agents. This keeps your writer agents sandboxed to read-only actions while leaving execution to a supervisor agent.

Yes, Vinkius runs the Crisp MCP Server in a dedicated, isolated sandbox. Your customer chat logs and contact details are transmitted securely and never exposed to external networks.

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