zulip (Windborne)

MCP开发工具

提供方 windborne

开发工具 未标注 会话登录 社区 / 第三方

Run AI agents in Zulip as @mentionable bots — or wire into any MCP client.

一句话选型结论

按资料字段整理

zulip (Windborne) 属于开发工具类 MCP 服务器,传输方式未标注,会话登录,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式未标注 鉴权会话登录 部署方式支持远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

安装与配置

未标注 会话登录
上游未给出传输方式
  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 基础信息齐全,可以先按官方文档接入试跑。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好会话登录对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
zulip (Windborne)当前 未标注 未标注 支持远程部署 无 2026-05-17
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方windborne上游标注的维护方 windborne
分类开发工具本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式会话登录远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型支持远程部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

17.0 KB
来自项目仓库与上游目录的原文,未做删改

zulipmcp

Run AI agents in Zulip as @mentionable bots — or wire into any MCP client. Also works as a Python library.

Quickstart

  1. Install the package:bash uv add git+https://github.com/windborne/zulipmcp.git

  2. Add a .zuliprc file 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."

  3. Add the MCP server to your .mcp.json:json { "mcpServers": { "zulip": { "command": "uv", "args": ["run", "python", "-m", "zulipmcp"] } } }

  4. Restart your MCP client. The Zulip tools should now be available.

Read as yourself, post as a bot

A bot can't read private channels it isn't in or DMs it isn't part of. To let an agent read everything you can see while it still posts as the bot, run two servers: one on the bot's zuliprc, and a read-only one on a zuliprc holding your personal API key. Installing the zulipmcp command once keeps launches from re-resolving dependencies:```bash
uv tool install git+https://github.com/windborne/zulipmcp.git # update later with: uv tool upgrade zulipmcp


`uv tool install` ignores the lockfile; append `@` to the URL to pin a version.

Desktop MCP clients often don't inherit your shell's `PATH`; if `zulipmcp` isn't found, use the absolute path under `uv tool dir --bin`.```json
{
  "mcpServers": {
    "zulip": {
      "command": "zulipmcp",
      "env": {"ZULIP_RC_PATH": "/path/to/bot.zuliprc"}
    },
    "zulip-personal": {
      "command": "zulipmcp",
      "env": {
        "ZULIP_RC_PATH": "/path/to/personal.zuliprc",
        "ZULIPMCP_READ_ONLY": "1",
        "BOT_ALLOWED_PRIVATE_STREAMS": "__ALL__"
      }
    }
  }
}

__ALL__ lets that server read DMs and search everything the account received. Read-only mode constrains this server, not an agent that can read the personal zuliprc file itself.

Requirements

  • Python >=3.10, managed with uv
  • Zulip Server 9.0+ (before date bounds need 12.0+)
  • A .zuliprc file for Zulip API auth (see Quickstart)
  • For listener mode: the selected backend CLI installed and authenticated (claude by default, codex with --backend codex, or opencode with --backend opencode)

Entry Points

Entry Point Description
uv run python -m zulipmcp (or zulipmcp after uv tool install) MCP server for Claude Code, Codex, and other MCP clients
uv run python -m zulipmcp --transport sse MCP server over SSE (for remote/web clients)
uv run python -m zulipmcp.launch_agent Launch one MCP-backed coding session without a listener
uv run python -m zulipmcp.listener Listener: watches for @mentions, spawns agent sessions

Library Usage

zulipmcp can also be imported directly as a Python library:```python
import zulipmcp

Fetch and format the latest page of a channel

page = zulipmcp.fetch_narrow(zulipmcp.build_narrow(stream="engineering"))
print(zulipmcp.format_messages(page.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}"),
auto_typing_start=False, # another process drives the typing indicator
)


## Hermes Gateway

Hermes uses the native `hermes_plugin/zulip` gateway
adapter instead of the subprocess listener. Each stream/topic maps to its own
persistent Hermes session, while zulipmcp remains available as the explicit
Zulip API tool layer.

- Mention the bot once to activate a topic; follow-ups do not need a mention.
- Each user message is a fresh Hermes turn with a fresh iteration budget.
- Typing, normal response delivery, status reactions, approval reactions,
  and `:stop_sign:` interruption are handled by the adapter.
- Only same-topic history is added on first activation.
- After a gateway restart, mention once to reactivate the topic; Hermes resumes
  the same stored session.

See the plugin README for installation,
configuration, access controls, and verification.

## Direct launch (no listener)

An existing coordinator can start one Claude Code or Codex session directly.
The coding agent uses its configured `zulip` MCP server to initialize the
target topic, reply there, and wait for follow-ups:```bash
python -m zulipmcp.launch_agent \
  --backend claude \
  --agent-command /path/to/claude \
  --stream engineering \
  --topic "large coding task" \
  --working-dir /path/to/project

python -m zulipmcp.launch_agent \
  --backend codex \
  --agent-command /path/to/codex \
  --stream engineering \
  --topic "large coding task" \
  --working-dir /path/to/project

The launcher does not watch Zulip or spawn on mentions. It starts exactly one
foreground coding-agent process and reuses the bundled session instructions.
Run it as a background process when the coordinator should continue working.
By default the agent listens in renewable two-hour intervals and does not exit
merely because an interval timed out.
Use --trigger-message-id and --session-user-email when that metadata is
available. Pass --zuliprc or --mcp-config only when the agent should not use
its existing global MCP configuration. An explicit Claude MCP config is loaded
strictly so a project-local server with the same name cannot shadow it.

Listener

The optional zulipmcp.listener module watches Zulip for @mentions and spawns one headless agent session per (stream, topic). It supports Claude Code by default, Codex with --backend codex, and OpenCode with --backend opencode. It's the glue between Zulip events and the agent backend -- the MCP server handles all the Zulip tools, the listener just handles lifecycle.```bash

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

Recommended: Claude Code with Opus 4.6

uv run python -m zulipmcp.listener -- --model claude-opus-4-6

Recommended: Codex with GPT-5.5 and medium reasoning

uv run python -m zulipmcp.listener --backend codex -- \
--model gpt-5.5 \
-c 'model_reasoning_effort="medium"'

Recommended: OpenCode with any provider (Qwen, Llama, Gemini, etc.)

uv run python -m zulipmcp.listener --backend opencode \
--opencode-model anthropic/claude-sonnet-4-5

uv run python -m zulipmcp.listener --backend opencode \
--opencode-model ollama/qwen3:235b

Pass additional backend-specific flags after --

uv run python -m zulipmcp.listener -- --strict-mcp-config --effort medium
uv run python -m zulipmcp.listener --backend codex -- -c 'model_verbosity="low"'
uv run python -m zulipmcp.listener --backend opencode -- --verbose
```

Flags:

Flag Default Description
--zuliprc ./.zuliprc Path to .zuliprc (resolved relative to current working directory)
--backend claude Agent backend to launch: claude, codex, or opencode
--agent-command backend name Backend CLI binary name or path
--mcp-config ./.mcp.json Path to .mcp.json for agent sessions (used only if the file exists). Codex translates supported command and url servers into one-run -c mcp_servers... overrides. OpenCode embeds the translated config in OPENCODE_CONFIG_CONTENT.
--system-prompt zulipmcp/default_system_prompt.md System prompt file. Claude receives it as an appended system prompt; Codex receives it as developer instructions; OpenCode receives it via the instructions config field.
--working-dir . Working directory for spawned sessions
--log-dir ./logs Directory for session log files
--codex-permission-mode parity Codex-only permission preset. parity uses --yolo for full bypass like the Claude default and assumes external sandboxing; workspace-write and read-only use noninteractive sandboxed modes; none adds no permission flags.
--opencode-model (none) OpenCode model in provider/model format (e.g. anthropic/claude-sonnet-4-5, ollama/qwen3:235b). When omitted, OpenCode uses its own default.
--opencode-agent (none) OpenCode agent name (passed as --agent). When omitted, OpenCode uses its default agent.
-- ... (none) Everything after -- is forwarded to the selected backend as-is. For Codex, known top-level-only flags are placed before exec automatically.

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 intentionally does not set model or reasoning defaults. Backend CLIs and model aliases move over time, so use the backend's user config or pass flags after --. For reproducible production behavior, pin exact backend model IDs in your deployment config instead of relying on aliases.

Custom --system-prompt files are backend instructions, not the initial task. The listener still sends a short per-session bootstrap prompt with the target stream/topic and the Zulip lifecycle contract: initialize context, send visible text through reply(), then call listen() when yielding for follow-ups.

Codex sessions launch with web search enabled to match Claude Code's default web-fetch capability. For Codex, the .mcp.json adapter whitelists inherited environment variable names for translated stdio MCP servers, mirroring Claude-style subprocess inheritance without putting env values in argv. It also forwards Zulip's direct auto-init SESSION_STREAM/SESSION_TOPIC pair when present and sets tool_timeout_sec to at least 3 hours so the long-running listen() tool can wait for follow-ups. The adapter is intentionally conservative: Claude SSE config is rejected, only command and streamable HTTP url servers are translated, and environment placeholders are supported only in env/header values that can stay out of process argv.

OpenCode sessions receive the full config via OPENCODE_CONFIG_CONTENT (inline JSON). The .mcp.json adapter translates command-based servers to OpenCode's local type (merging command+args into a single array) and url-based servers to remote type, renaming env to environment. Each translated server gets a 3-hour MCP timeout so listen() can block for follow-ups; listen() sends MCP progress notifications during its long-poll loop, which OpenCode uses to reset its per-call timeout. The system prompt file path is passed via the instructions config field.

The listener is deliberately minimal. 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.

An ear emoji is added to the last message as a visual indicator while listening and removed when listening stops. If the realm has a custom emoji named robot_ear, that is used instead. 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"}).

Typing indicator

The typing indicator starts on set_context() and after every reply(), and stops on listen() and end_session(), so users see the bot as "typing" while it works. If another process drives the indicator, configure(auto_typing_start=False) suppresses the automatic starts so they cannot overwrite it; the stops still run, since clearing the indicator on idle and exit is right whoever set it, and reply() sends a stop in place of its start so the status shown while composing does not outlive the message. The explicit typing() / stop_typing() tools are unaffected.

Reading history and search

get_messages reads one conversation (stream+topic, dm_with, or up to a message_id); search_messages wraps Zulip's native keyword search over a stream, everything this account received (scope="received"), or all public channels (scope="public", the default without __ALL__). Both page backward with the before_message_id each response names and accept ISO 8601 after/before bounds (before needs Zulip 12.0+). Both filter with only (unread, mentioned, starred, plus dm on search; ANDed); search_messages adds dm_including and max_chars (clips each hit). Formatted messages are tagged mentioned="true" when they mention this account and, on human accounts, unread="true".

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.

Outgoing markdown normalization

normalize_zulip_markdown() runs on every send/reply/edit before content hits the API, fixing two GFM habits Zulip's renderer mishandles: missing blank lines before tables, and bold combined with links (**a** renders as literal asterisks with an unclickable link; a bare URL touching ** breaks the autolink). Fenced and indented code blocks are always left untouched; inline code spans are additionally preserved for the bold/link fix. The Hermes gateway sends via the raw client and is not normalized. Disable entirely with ZULIPMCP_MARKDOWN_AUTOFIX=0.

Environment Variables

Variable Description
ZULIP_RC_PATH Absolute path to .zuliprc for direct MCP server or Hermes gateway use. Listener mode sets this for spawned sessions from --zuliprc; it does not read ambient ZULIP_RC_PATH as its own default.
ZULIPMCP_TIMEZONE IANA timezone used to display message timestamps and to interpret date-only and naive after/before values, such as Europe/London or Asia/Tokyo. Defaults to America/Los_Angeles.
ZULIP_MAX_MESSAGE_LENGTH Char limit above which send tools return an error instead of letting Zulip silently truncate. Defaults to 10000 (Zulip's default); set for realms with a custom cap.
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. Without __ALL__, reads must name an allowed stream or public channels, and DMs are refused; with it, search_messages defaults to scope="received".
BOT_ALLOWED_WRITE_STREAMS Stream send allowlist. Unset = writes allowed everywhere (backwards-compatible). Same formats as above.
ZULIPMCP_READ_ONLY 1/true/yes/on: the client refuses every non-GET request, and write and session tools are hidden. Unset, empty or 0/false/no/off = off; anything else is a startup error. See Read as yourself, post as a bot.
ZULIPMCP_CACHE_DIR Override the disk cache base directory (defaults to system temp dir). Each site and account gets its own subdirectory, so servers running as different users never share cached data.
ZULIPMCP_LOG_DIR Server log directory (defaults to /tmp/zulipmcp_logs); written by run_server(), never on import.
ZULIPMCP_MARKDOWN_AUTOFIX Disables all outgoing markdown normalization (blank-line-before-table injection and bold/link rewrites) when set to 0 or false. Defaults to enabled.

License

Apache 2.0

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
zulip (Windborne) 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

zulip (Windborne) 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

zulip (Windborne) 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

zulip (Windborne) 需要 API Key 吗?

资料标注需要会话登录认证,使用前准备好对应凭据,并按最小权限配置。

zulip (Windborne) 能提供哪些能力?

资料显示能力标签包括 Session认证、开发工具、命令行工具。具体工具清单以官方文档为准。

zulip (Windborne) 需要什么运行环境?

属于远程端点,不需要在本地装运行时。

zulip (Windborne) 是本地还是远程?

它是远程端点,连服务地址即可。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。