The Zulip MCP Server acts as a bridge between the Zulip chat platform and AI assistants like Claude. Essentially, it gives an AI the ability to "talk" and "listen" within a Zulip workspace. Instead of a user having to copy and paste conversations or manually post status updates, this tool lets the AI handle those tasks directly, making team communication more fluid and automated. For developers and power users, this server unlocks a wide range of collaborative capabilities. It provides specific tools for listing channels, reading message history, and managing topics within streams. It can even handle interactive elements like adding emoji reactions or sending direct messages to specific team members. By subscribing to certain streams and pulling historical data, the AI can stay informed about ongoing projects and provide context-aware assistance based on actual team discussions. On a technical level, the integration is built to work seamlessly with the Model Context Protocol, allowing for easy deployment via npx or Docker. It interfaces directly with the Zulip API using a dedicated bot account, requiring only a few environment variables such as an API key and instance URL. This setup is particularly powerful for building custom AI agents that need to monitor specific threads, summarize daily activity, or act as an automated project manager that can post updates to specific topics within a workspace.
Category: Communication & Messaging
Tags: chat, collaboration, messaging, zulip
https://example.zulipchat.com) 3. Permissions: Ensure the bot is subscribed to the specific channels (streams) it needs to access. For Docker users, you can build the image locally: bash docker build -t mcp/zulip .claude_desktop_config.json).json { "mcpServers": { "zulip": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-zulip" ], "env": { "ZULIP_EMAIL": "your-bot@example.zulipchat.com", "ZULIP_API_KEY": "your-bot-api-key", "ZULIP_URL": "https://example.zulipchat.com" } } } }json { "mcpServers": { "zulip": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "ZULIP_EMAIL", "-e", "ZULIP_API_KEY", "-e", "ZULIP_URL", "mcp/zulip" ], "env": { "ZULIP_EMAIL": "your-bot@example.zulipchat.com", "ZULIP_API_KEY": "your-bot-api-key", "ZULIP_URL": "https://example.zulipchat.com" } } } }zulip_list_channels: List available channels (streams). Optional inputs: include_private, include_web_public, include_subscribed. * zulip_post_message: Post a new message to a stream. Required inputs: channel_name, topic, content. * zulip_send_direct_message: Send a DM to one or more users. Required inputs: recipients (array of emails/IDs), content. * zulip_add_reaction: Add an emoji reaction to a message. Required inputs: message_id, emoji_name. * zulip_get_channel_history: Get recent messages from a channel and topic. Required inputs: channel_name, topic. * zulip_get_topics: Get topics within a specific channel. Required input: channel_id. * zulip_subscribe_to_channel: Subscribe the bot to a channel. Required input: channel_name. * zulip_get_users: Retrieve a list of users in the Zulip organization.zulip_get_channel_history, processes the messages, and provides a bulleted summary of the consensus reached by the team.zulip_get_users to identify the recipient and zulip_post_message to share the code.zulip_get_topics and zulip_get_channel_history to find past discussions in the #dev-ops stream, then explains the process based on those historical conversations.Part of MCP Servers
Zulip MCP Server is an open source bridge connecting the Zulip messaging platform to AI assistants using the Model Context Protocol. It allows assistants to post messages, read topic histories, and manage stream interactions via standard Zulip API endpoints.
Create a generic bot in your Zulip workspace to generate an API key and email. Then, register the server in your MCP client configuration using the npx command pointing to @modelcontextprotocol/server-zulip or by building and running the provided Dockerfile.
The server provides tools to list channels, post messages to streams, send direct messages, add emoji reactions, fetch message history by channel and topic, inspect topics within streams, subscribe to channels, and retrieve organization user lists.
Zulip MCP Server works with any client supporting the Model Context Protocol, including Claude Desktop and Cursor, when configured with the appropriate executable and environment variables.
Yes, Zulip MCP Server is open source and distributed under the Apache License, Version 2.0. The source code and repository details are hosted on GitHub by Monadical.