zulip
Run AI agents in Zulip as @mentionable bots — or wire into any MCP client.
README
zulipmcp
Run AI agents in Zulip as @mentionable bots — or wire into any MCP client. Also works as a Python library.
<img width="1446" height="752" alt="zulipmcp in action" src="https://github.com/user-attachments/assets/6e6bbed7-ed19-4c4a-a9f2-48468dc9a570" />
Quickstart
-
Install the package:
uv add zulipmcp --git https://github.com/windborne/zulipmcp.git -
Add a
.zuliprcfile to your project root with your Zulip bot credentials. See Add a bot or integration for instructions on making a bot. The bot type must be "generic." -
Add the MCP server to your
.mcp.json:{ "mcpServers": { "zulip": { "command": "uv", "args": ["run", "python", "-m", "zulipmcp.mcp"] } } } -
Restart your MCP client. The Zulip tools should now be available.
Requirements
- Python >=3.10, managed with uv
- A
.zuliprcfile for Zulip API auth (see Quickstart)
Entry Points
| Entry Point | Description |
|---|---|
uv run python -m zulipmcp.mcp |
MCP server for Claude Code / MCP clients |
uv run python -m zulipmcp.mcp --transport sse |
MCP server over SSE (for remote/web clients) |
uv run python -m zulipmcp.listener |
Listener: watches for @mentions, spawns Claude Code sessions |
Library Usage
zulipmcp can also be imported directly as a Python library:
import zulipmcp
# Fetch and format recent messages
messages = zulipmcp.get_messages(hours_back=24, channels=["engineering"])
print(zulipmcp.format_messages(messages))
# Send a message
zulipmcp.send_message("engineering", "general", "Hello from Python!")
# Configure MCP hooks before starting the server
zulipmcp.configure(
message_prefix=lambda: "[bot] ",
on_session_end=lambda session: print(f"Session ended in #{session.stream}"),
)
Listener
The optional zulipmcp.listener module watches Zulip for @mentions and spawns one headless Claude Code session per (stream, topic). It's the glue between Zulip events and Claude Code -- the MCP server handles all the Zulip tools, the listener just handles lifecycle.
# Minimal -- uses ./.zuliprc, ./.mcp.json (if present), and the bundled default prompt
uv run python -m zulipmcp.listener
# Full -- override MCP config and system prompt
uv run python -m zulipmcp.listener \
--mcp-config .mcp.json \
--system-prompt agent.md \
--log-dir ./logs
# Pass flags through to Claude Code (everything after --)
uv run python -m zulipmcp.listener -- --strict-mcp-config --model opus
Flags:
| Flag | Default | Description |
|---|---|---|
--zuliprc |
./.zuliprc |
Path to .zuliprc (resolved relative to current working directory) |
--mcp-config |
./.mcp.json |
Path to .mcp.json for Claude Code sessions (used only if the file exists) |
--system-prompt |
zulipmcp/default_system_prompt.md |
Appended system prompt file (default path is resolved relative to listener.py, not the current working directory) |
--working-dir |
. |
Working directory for spawned sessions |
--claude-command |
claude |
Claude CLI binary name or path |
--log-dir |
./logs |
Directory for session log files |
-- ... |
(none) | Everything after -- is forwarded to claude as-is |
Each session gets TRIGGER_MESSAGE_ID and SESSION_USER_EMAIL set automatically so set_context() anchors to the @mention and hooks can identify the requester.
The listener is deliberately minimal (~230 lines). It omits concurrency caps, workspace isolation, staleness watchdogs, and dashboards -- add those when you need them.
Key Design Details
Listening for messages
The listen tool uses Zulip's real-time events API (long-polling) instead of repeated GET /messages calls. On entry it catches up on any messages since last_seen_message_id, subscribes the bot to the stream if needed, registers a narrowed event queue for the stream/topic, and then long-polls via GET /events. The server blocks until a message arrives or ~90 seconds elapse (heartbeat), making this ~30x more efficient than polling every 2 seconds. If the queue expires (BAD_EVENT_QUEUE_ID), it re-registers automatically. The queue is deleted in a finally block on exit.
A robot_ear emoji is added to the last message as a visual indicator while listening and removed when listening stops. MCP keepalive pings are sent via ctx.info() after each long-poll cycle.
No missed messages on reply
When reply is called, it checks for new messages before sending. If anyone posted while the LLM was thinking, those messages are fetched and returned alongside the "message sent" confirmation. This way the LLM always sees what it missed and can react accordingly. The last_seen_message_id is updated to whichever is newest -- the missed messages or the sent message -- so nothing falls through the cracks.
Session dismissal
Users can dismiss a bot session by reacting with a configurable emoji (default: :stop_sign:) on any bot message. The dismiss check runs both during listen() (via reaction events) and before reply() (via REST API poll), covering the race condition where a user reacts while the bot is busy working. Customize with configure(dismiss_emoji={"stop_sign", "wave"}).
Bot visibility filtering
Topics containing /nobots or /nb are hidden from the bot entirely. Messages starting with /nobots or /nb are also filtered out. This lets humans have private conversations the bot won't see.
Environment Variables
| Variable | Description |
|---|---|
ZULIP_RC_PATH |
Absolute path to .zuliprc. Overrides the default (./.zuliprc in cwd). |
TRIGGER_MESSAGE_ID |
Message ID that triggered the session (e.g. the @mention). Sets the listen anchor so the agent doesn't miss messages after the trigger. |
SESSION_USER_EMAIL |
Email of the human who triggered the session. Stored on SessionState for hooks. |
SESSION_STREAM |
Stream name for auto-initializing a session on server start (direct run_server() callers only -- the listener does not use these). Both SESSION_STREAM and SESSION_TOPIC must be set; the agent can then skip set_context(). |
SESSION_TOPIC |
Topic for auto-init. Requires SESSION_STREAM. |
BOT_ALLOWED_PRIVATE_STREAMS |
Private-stream read/send allowlist. Unset = no private-stream access. Accepts __ALL__, a JSON list, or comma-separated names. |
BOT_ALLOWED_WRITE_STREAMS |
Stream send allowlist. Unset = writes allowed everywhere (backwards-compatible). Same formats as above. |
ZULIPMCP_CACHE_DIR |
Override the disk cache directory (defaults to system temp dir). |
ZULIPMCP_LOG_DIR |
Override the log directory (defaults to /tmp/zulipmcp_logs). |
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.