How to Use the Zulip MCP in OpenAI Agents SDK

Q: Does Zulip and OpenAI Agents SDK handle private messages?

Yes, it does. The zulipsendmessage tool accepts the 'direct' type. This means your agent can send DMs between users just like a human would on Zulip.

Build production agents for Zulip using the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Zulip to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send messages via the MCP Server

Need to notify someone? The `zulip_send_message` tool lets your agent post a message, whether it’s going into a specific stream or as a direct chat. You specify the type—'stream' for channels or 'direct' for DMs—and hit send. This is perfect for automated reminders or status updates. Your agent handles the connection and formatting so you don't have to write boilerplate code around messaging logic.

Check message history with OpenAI Agents SDK

You can retrieve full message history using `zulip_get_messages`. Just use the anchor parameter; setting it to 'newest' gets you the latest messages right away. This means your agent always has fresh context when it needs to answer a question. If you need historical data, this tool pulls everything in so your specialized agents can read through past conversations for context before making decisions.

Manage users and streams

The MCP Server exposes tools to handle the organizational structure. Use `zulip_get_streams` to list every stream available, or run `zulip_get_users` to get a full directory of people in your organization. Before an agent can do anything complex, it needs to know where things are located. These listing tools give your production system the map it needs to operate safely.

Setup guide

Set up Zulip MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Zulip tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Zulip tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Zulip tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Zulip Agent",
            instructions="You have access to Zulip tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent uses the authenticated bot/user profile, which you fetch with `zulip_get_own_profile`. This tool confirms exactly what scope your agent operates under. The built-in guardrails validate actions before they run, so over-permissioning is handled automatically.

Absolutely. Since this framework supports handoffs between specialized agents, you can chain tools together. For example, one agent might list streams using `zulip_get_streams`, and the next agent uses that output to send a message via `zulip_send_message`.

Yes, it does. The `zulip_send_message` tool accepts the 'direct' type. This means your agent can send DMs between users just like a human would on Zulip.

You primarily interact with message content, stream metadata (topics), user lists, and the authenticated bot profile details. These are all standard organizational data points within Zulip.

This server touches message content and stream metadata. Since you're building a production system, always ensure your guardrails restrict access to only the necessary scope of messages and streams.

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