How to Use the Coze MCP in AutoGen

Q: Can AutoGen agents collaborate on a Coze chat session?

Yes. One AutoGen agent can initiate the chat using createchat, while another reviews the history using getconversationhistory to decide if the bot's response is accurate.

Q: How do I configure the Coze MCP Server inside an AutoGen group chat?

Use autogen-extmcp to load the tools via the Vinkius HTTP endpoint. Pass the resulting tool list to your AssistantAgent so any agent in the group can call them.

Q: Can AutoGen agents manage multiple Coze workspaces?

Yes. Agents can query available environments using listworkspaces and coordinate which datasets to update using listdatasets across different teams.

Let your AutoGen agents debate, deploy, and manage Coze bots through collaborative multi-agent workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coze MCP to AutoGen

Create your Vinkius account to connect Coze 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 Coze with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Coze bot deployment with AutoGen agents

This MCP Server allows your AutoGen developer agent to build and deploy Coze bots while a separate QA agent reviews them. The AutoGen developer agent uses `publish_bot` to go live only after the QA agent approves the workspace setup found via `list_workspaces`. This consensus-driven approach ensures that no broken Coze bots are published. The AutoGen agents communicate back and forth, checking the bot list with `list_bots` before finalizing the deployment.

Multi-agent conversation and chat history analysis

This MCP Server lets your AutoGen analyst agent use `get_conversation_history` to pull logs from a Coze session and share them with the group. The AutoGen agents then debate the quality of the Coze bot's responses. If the Coze conversation goes off track, the AutoGen moderator agent calls `clear_conversation` to reset the state. A new Coze chat session is then started using `create_chat` with updated system prompts.

Consensus-driven dataset curation in AutoGen

This MCP Server lets your AutoGen data agent use `upload_document` and `upload_file_url` to add files to a Coze knowledge base. Before doing so, it debates with an AutoGen security agent to ensure the files do not contain sensitive info. If the AutoGen security agent flags an issue, the data agent calls `delete_document` to remove the file from Coze. This keeps your Coze datasets secure and compliant without manual oversight.

Setup guide

Set up Coze 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 Coze 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="Coze_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Coze 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="Coze_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Coze 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 Coze. 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 Coze 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 Coze MCP in AutoGen

Yes. One AutoGen agent can initiate the chat using `create_chat`, while another reviews the history using `get_conversation_history` to decide if the bot's response is accurate.

When a bot requires external data, your AutoGen execution agent runs the required task and calls `submit_tool_outputs` to feed the result back to the running chat session.

Use `autogen-ext[mcp]` to load the tools via the Vinkius HTTP endpoint. Pass the resulting tool list to your `AssistantAgent` so any agent in the group can call them.

Yes. Agents can query available environments using `list_workspaces` and coordinate which datasets to update using `list_datasets` across different teams.

Yes. Your token is stored securely in Vinkius and injected only inside the secure V8 sandbox execution environment. AutoGen agents never see the raw API key during tool execution.

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