How to Use the Zulip MCP in AutoGen

Q: How does AutoGen handle Zulip messaging?

Agents use zulipsendmessage to communicate. They negotiate the content, recipient (stream or direct), and timing of the message before sending it.

Q: Can I get user lists for my Zulip chat with AutoGen?

Yes. An agent calls zulipgetusers to gather all organizational users, which can then be debated and filtered by the team of autonomous agents.

Q: What is the data privacy scope of this Zulip MCP Server?

This server touches user profile information (zulipgetownprofile), stream membership details, and message content retrieved through zulipgetmessages.

Q: Does AutoGen need specific access for Zulip streams?

Yes. The agents might first call zulipgetstreams, and then one agent must explicitly use zulipsubscribetostream to ensure the chat data is available.

Run multi-agent Zulip workflows using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zulip MCP to AutoGen

Create your Vinkius account to connect Zulip 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 Zulip with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulate chat agent debates

AutoGen allows multiple agents to discuss and challenge conclusions based on real data. One agent can fetch a list of users via `zulip_get_users`, while another proposes an action like sending a message using `zulip_send_message`. The agents then debate the optimal communication strategy, simulating consensus-driven decision making before any chat action is taken.

Manage and monitor Zulip streams

Agents can autonomously manage the workspace. They use `zulip_get_streams` to map out all available channels and then decide if they need to subscribe using `zulip_subscribe_to_stream`. If a new topic emerges, an agent can monitor it using `zulip_get_stream_topics`, leading to a multi-agent discussion about the next steps.

Handle message reactions and history retrieval

When reviewing chat logs, one agent uses `zulip_get_messages` to pull the historical context. A second agent then decides if a specific outcome requires acknowledgment, leading it to call `zulip_add_reaction`. This process allows for complex conversational responses that are guided by both retrieved history and immediate action.

Setup guide

Set up Zulip 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 Zulip 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="Zulip_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Agents use `zulip_send_message` to communicate. They negotiate the content, recipient (stream or direct), and timing of the message before sending it.

Yes. An agent calls `zulip_get_users` to gather all organizational users, which can then be debated and filtered by the team of autonomous agents.

This server touches user profile information (`zulip_get_own_profile`), stream membership details, and message content retrieved through `zulip_get_messages`.

Yes. The agents might first call `zulip_get_streams`, and then one agent must explicitly use `zulip_subscribe_to_stream` to ensure the chat data is available.

The agents will run through their deliberation process. If they reach consensus, one agent executes `zulip_send_message`. The action is only taken after the debate concludes.

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