原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Partiful MCP Server and API by Cotlet

作者:cotletdev版本 1.0.4i★ 7i电脑或云端
注册名称dev.cotlet/partiful

安装方法

概览

作者提供的说明(英文原文)

Partiful party invitations and rsvps MCP server: create invite, list RSVPs, export guest list.

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用,然后复制设置。

通过 4/5 项检查 · 你的提问会经过开发者的服务器(cotlet.dev)

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1+ Add2https://…3Add4
  2. 点击“+ Add” → “Add custom connector”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称Partiful MCP Server and API by Cotlet
    Remote MCP server URL · 地址https://cotlet.dev/mcp/v1/partiful/connect

    Authentication 保持 Claude 检测到的设置,然后点击 Add

  3. 在聊天中开启

    +ConnectorsPartiful MCP Server and API by Cotlet

  4. 试一试

    用 Partiful MCP Server and API by Cotlet 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Partiful MCP Server and API by Cotlet,或回答中出现 Partiful MCP Server and API by Cotlet 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

仅企业版 ChatGPT 可连接

适用于网页版 ChatGPT Business、Enterprise 或 Edu,需由工作区管理员或所有者添加 · 使用 Free、Plus 或 Pro:你的 ChatGPT 方案暂时无法自行连接 MCP

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称Partiful MCP Server and API by Cotlet
    Connection · 地址https://cotlet.dev/mcp/v1/partiful/connect
  3. 在聊天中选择 Partiful MCP Server and API by Cotlet

    开启新聊天,输入前先从插件列表中选择 Partiful MCP Server and API by Cotlet

  4. 试一试

    用 Partiful MCP Server and API by Cotlet 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 Partiful MCP Server and API by Cotlet,或回答中出现 Partiful MCP Server and API by Cotlet 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http partiful https://cotlet.dev/mcp/v1/partiful/connect
  3. 在 Claude Code 中输入 /mcp

    应能看到 Partiful MCP Server and API by Cotlet 在列表中并显示已连接

  4. 试一试

    用 Partiful MCP Server and API by Cotlet 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 Partiful MCP Server and API by Cotlet,或回答中出现 Partiful MCP Server and API by Cotlet 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Partiful MCP Server and API by Cotlet 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 Partiful MCP Server and API by Cotlet,或回答中出现 Partiful MCP Server and API by Cotlet 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Partiful MCP Server and API by Cotlet 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 Partiful MCP Server and API by Cotlet,或回答中出现 Partiful MCP Server and API by Cotlet 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://cotlet.dev/mcp/v1/partiful/connect

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Partiful MCP Server and API by Cotlet 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http partiful https://cotlet.dev/mcp/v1/partiful/connect

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "partiful": {
      "url": "https://cotlet.dev/mcp/v1/partiful/connect"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "partiful": {
      "type": "http",
      "url": "https://cotlet.dev/mcp/v1/partiful/connect"
    }
  }
}

安装在电脑上

Claude Code

claude mcp add partiful -- uvx partiful-api-mcp mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "partiful": {
      "command": "uvx",
      "args": [
        "partiful-api-mcp",
        "mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "partiful": {
      "command": "uvx",
      "args": [
        "partiful-api-mcp",
        "mcp"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "partiful": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "partiful-api-mcp",
        "mcp"
      ]
    }
  }
}

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
139/周
已验证域名
✓ cotlet.dev
许可证i
未注明许可证
连接方式
电脑或云端
传输方式
stdio, streamable-http
最新版本i
1.0.4
分类i
其他
发布到注册中心i
2026年11月10日
代码最后更新i
2026年11月11日
作者
cotletdev
软件包
pypi: partiful-api-mcp
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

服务器要求先登录,才会列出它的工具。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月11日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 cotlet.dev 验证(注册中心会核实域名所有权)

  • ✓ 通过

    仍在维护

    代码最后更新于今天

  • ! 注意

    有许可证

    GitHub 无法识别许可证类型;请打开文件自行查看

  • ✓ 通过

    端点有响应

    在 51 毫秒内响应(HTTP 401)

  • ✓ 通过

    使用 OAuth 登录

    声明支持 OAuth 登录,你的 AI 应用可以带你去登录

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

使用 Google 登录后发帖

用户评价

还没有评价

用 Google 登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 19144 个服务器的 96%
  • 发布到注册中心的时间比此分类中其他 19144 个服务器的 97% 更新
  • 基础检查结果等于或优于此分类中其他 19144 个服务器的 44%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Partiful MCP Server and API by Cotlet 安全吗?

它在 5 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于今天,最新版本(1.0.4)于今天进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于支持远程 MCP 的应用,例如 ChatGPT Business 及以上方案。

有什么可以替代它?

同一分类中有:World Monitor, Claude Flow, Tldraw

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 102 tools.

作者:koala73广泛使用★ 9万6天前更新

在云端运行✓ worldmonitor.app

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

作者:ruvnet广泛使用↓ 1.4万/周★ 8.1万14个月前更新

在你的电脑上运行

Tldraw

Draw and visually collaborate with your agents on tldraw's canvas.

作者:tldraw广泛使用★ 5.1万8个月前更新

在云端运行

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Partiful API and MCP server: connect Partiful to ChatGPT and Claude

Yes, ChatGPT, Claude and other AI agents can work in your Partiful account. That includes Cursor, Codex, OpenClaw and any MCP client, plus automations in n8n, Make and Zapier. Ask in plain words, and the AI creates events, sends updates to guests, reads RSVPs and exports guest lists. It shows you what it will do first and sends nothing to other people until you say so.

As of November 2026, this repo is the missing piece: 14 Partiful tools for AI assistants and scripts.

What you can ask

*Who is going to Friday's dinner, and what dietary restrictions did they put in the questionnaire?*

*Approve all pending guests to my launch party who answered with a company name, and list the rest for me.*

*Copy last month's book club for November 14 at 7pm and invite the people who came.*

*Text everyone who is Going or Maybe to my rooftop dinner that the door code is 4512.*

Two ways to get it

Ready to use, at CotletRun it yourself, this repo
Forhosts, community organisers and event teamsdevelopers
Setupsign in to Partiful once, about 5 minutes, nothing to installPython and a terminal
Works inChatGPT and Claude apps, on your phone too, Cursor, Codex, OpenClaw, any MCP client, n8n, Make, Zapier, REST APIClaude Code, Claude Desktop, Cursor, Codex on your computer
Runs24/7, your computer can be offwhile your computer is on
Price7 days free, no cardfree

Cotlet is best for hosts, community organisers and event teams who want ChatGPT, Claude or another AI agent to work in Partiful for them, with nothing to install.

[Start free at cotlet.dev →](https://cotlet.dev/signup?app=partiful&utm_source=github&utm_medium=readme&utm_campaign=partiful&utm_content=top-button)

Run it yourself

A Partiful API and a Partiful MCP server you run on your own computer, in Python, on the session of your own Google Chrome. All 14 Partiful tools we run in production at Cotlet: events, guest lists with questionnaire answers, the Export CSV file, check-in, Guest Approval, invites and Text Blasts.

Partiful has no public API and no official MCP server. This repo gives you both:

  • MCP server for Claude Code, Claude Desktop, Cursor, Codex and any MCP client, over stdio or HTTP. Setup
  • REST API on http://127.0.0.1:8787/api/v1/partiful, with OpenAPI docs at /docs. Setup
  • Python: call("list_guests", event_id="..."), plus 9 ready scripts in examples/.

Free for your own use, your own business included (license).

uv tool install partiful-api-mcp                  # or: pip install partiful-api-mcp

partiful-mcp connect # reads your Partiful session from Chrome partiful-mcp call list_events claude mcp add partiful -- uvx partiful-api-mcp mcp

Contents

  • Questions from Partiful users
  • How it works
  • Requirements
  • Install
  • Connect your Chrome
  • MCP server
  • REST API
  • Python and the example scripts
  • All 14 tools
  • Configuration
  • Security and your Partiful account
  • Errors
  • Self-hosted or hosted
  • FAQ
  • License

Questions from Partiful users

Does Partiful have an API? No. Partiful has no public API, no developer docs and no webhooks, and its help center documents no Zapier or Make connection. Guest data leaves Partiful only as a CSV you export by hand with the Export CSV button. This repo and Cotlet give you 14 Partiful tools as a REST API and an MCP server.

Can I get a Partiful API key? Not from Partiful for your own account. With Cotlet you get your own API key that works with your Partiful account, for scripts, n8n, Make, Zapier or any HTTP client. This repo needs no key: it runs on your computer, on your own Partiful session.

Is there an official ChatGPT integration for Partiful? No. Partiful has no official ChatGPT or Claude connector. Cotlet is an unofficial one that works today, in the ChatGPT and Claude apps and in any AI agent that takes an MCP server.

How do I connect Partiful to ChatGPT? Sign up at cotlet.dev, sign in to Partiful once in your Cloud Browser there, and add Cotlet to ChatGPT, following the steps in your account. Then ask ChatGPT about your Partiful like you would ask an assistant. ChatGPT needs a server on the internet, so this repo alone, running on your computer, does not connect to ChatGPT.

Can ChatGPT create Partiful events for me? Yes, with Cotlet. Describe the event, and it creates it with the time, place and description, then texts updates to guests after your OK.

Can I export my Partiful guest list? Yes, with Cotlet: guests, RSVPs and answers to your questions for any event, without clicking Export CSV.

Can I automate Partiful with Zapier, Make or n8n? Partiful has no Zapier or Make app. With Cotlet, n8n, Make and Zapier can create events and read RSVPs, for example into a sheet or your CRM.

Can I use it from my phone? Yes, with Cotlet: once it is set up, the ChatGPT and Claude apps on your phone can use Partiful for you.

Do I need to be technical? For Cotlet, no: you sign in to Partiful and add Cotlet to ChatGPT or Claude, with step-by-step instructions in your account. This repo is for people who are fine with Python and a terminal.

Is my Partiful account safe? Yes. Neither Cotlet nor this repo sees or stores your Partiful password. You sign in yourself, the way you always do, and the AI works on that signed-in session. Anything that reaches other people asks for your OK first: in Cotlet by default, here through your MCP client.

Is it free? This repo is free, also in your own business. Cotlet is free for 7 days with no card, then one-time credit packs from $29, no subscription. Pricing.

I manage Partiful for several accounts or clients. Does that work? Yes, with Cotlet. Each Partiful login gets its own connection. Write to contact@cotlet.dev and tell us how many accounts you manage.

How it works

AI agent (MCP) / script (REST, Python) ──▶ partiful-mcp on your computer ──your Partiful sign-in──▶ api.partiful.com

▲ Firestore partiful-mcp connect ───────┘ reads it once from your Chrome (DevTools Protocol)

  1. You sign in to Partiful in your own Chrome, with your phone number and the code Partiful texts you.
  2. partiful-mcp connect attaches to that Chrome through the Chrome DevTools Protocol. It reads the partiful.com cookies and, from a partiful.com tab, the signed-in user that the Partiful web app keeps in IndexedDB (Firebase, with its refresh token). If no Partiful tab is open, it opens one in the background and closes it again. Both are saved to ~/.config/partiful-api-mcp/session.json, readable by your user only.
  3. Every tool call is a request to the endpoints the Partiful web app calls itself: its functions on api.partiful.com, and Firestore for guest lists and event edits. Requests go out with curl_cffi, which copies Chrome's TLS fingerprint. No headless browser runs.

Partiful's sign-in token lasts an hour. The server renews it from the saved refresh token at Google's securetoken.googleapis.com, the way the web app does, so you connect once and not every hour. When Partiful ends the session, the server reads it from Chrome again, if Chrome is open with remote debugging on.

Requirements

  • Python 3.11 or newer.
  • Google Chrome 144 or newer, signed in to Partiful on partiful.com. Any Chrome or Chromium works with a debugging port.
  • macOS, Linux or Windows.
  • A Partiful account that hosts the events. Reading and changing an event's guest list, approvals, check-in, invites and Text Blasts work for events you host or cohost. get_event opens any event your account can see.

Install

From PyPI:

uv tool install partiful-api-mcp       # or: pipx install partiful-api-mcp, or: pip install partiful-api-mcp

partiful-mcp --version

MCP clients can also run it with no install: uvx partiful-api-mcp mcp.

From source:

git clone https://github.com/cotletdev/partiful-api-mcp-server.git

cd partiful-api-mcp-server python3 -m venv .venv . .venv/bin/activate # Windows: .venv\Scripts\activate pip install -e . partiful-mcp --version

With uv: uv venv && uv pip install -e ., then uv run partiful-mcp ....

Setting it up with an AI agent (Claude Code, Codex, Cursor)? Open it in this folder and ask it to set up the repo: AGENTS.md tells it every step, and it asks you only for the steps in Chrome.

To update: uv tool upgrade partiful-api-mcp (or pip install -U partiful-api-mcp), from source git pull && pip install -e .. We copy every change of the hosted Partiful tools into this repo.

Connect your Chrome

Option A: your everyday Chrome (recommended)
  1. Open chrome://inspect/#remote-debugging in Chrome and switch remote debugging on. Chrome then accepts DevTools connections from programs on this computer, and asks you before each one.
  2. Make sure you are signed in at partiful.com.
  3. Run:
   partiful-mcp connect
  1. Chrome asks whether to allow the connection. Click Allow.
Saved 16 Partiful cookies and 1 sign-in keys to /Users/you/.config/partiful-api-mcp/session.json

Signed in to Partiful as Maya Chen

You can switch remote debugging off again afterwards. Leave it on if you want the server to pick up a new session by itself after Partiful signs you out.

connect looks for Chrome's DevToolsActivePort file in the default profile folder. For Chrome Beta, Canary or a custom profile folder, pass --profile-dir " ".

Option B: a Chrome with a debugging port

Chrome does not open a debugging port on your default profile, so start a separate one, sign in to Partiful there once, and connect to it:

# macOS

"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --remote-debugging-port=9222 --user-data-dir="$HOME/.chrome-partiful"

Linux

google-chrome --remote-debugging-port=9

只显示了开头部分;其余内容请在仓库中阅读