Calendly MCP Server
Exposes personal Calendly account as MCP tools, allowing users to manage events, view availability, and handle bookings through natural language.
README
Calendly MCP Server
A minimal MCP server that exposes your personal Calendly account to Claude (or any MCP client) as a set of tools, using a Personal Access Token.
Tools included
get_current_user— your profile infolist_event_types— your bookable event types (e.g. "30 Minute Meeting")list_scheduled_events— bookings on your calendarget_scheduled_event— full details of one bookinglist_event_invitees— who booked, and their answers to your questionscancel_scheduled_event— cancel a bookingget_event_type_available_times— open slots for an event typecreate_scheduling_link— generate a single-use booking link to share
1. Get a Calendly Personal Access Token
- Log into Calendly in your browser.
- Go to Account Settings → Integrations → API & Webhooks.
- Under Personal Access Tokens, click Generate New Token, name it (e.g. "MCP Server"), and copy the value — Calendly only shows it once.
2. Install dependencies
cd calendly-mcp
python3 -m venv venv
source venv/bin/activate # on Windows: venv\Scripts\activate
pip install -r requirements.txt
3. Configure your token
cp .env.example .env
Open .env and paste your token in place of the placeholder:
CALENDLY_API_TOKEN=your_actual_token_here
4. Test it locally with the MCP Inspector
mcp dev server.py
This opens a local web UI where you can call each tool directly and see the raw Calendly API responses — the fastest way to catch bugs before wiring it into a client.
5. Connect it to Claude Desktop
Local (stdio) MCP servers like this one run through Claude Desktop or Claude Code, not the claude.ai web/mobile app (which only connects to remote/hosted MCP servers via its connector picker).
Open Claude Desktop's config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add an entry (use the absolute path to your venv's python and server.py):
{
"mcpServers": {
"calendly": {
"command": "/absolute/path/to/calendly-mcp/venv/bin/python",
"args": ["/absolute/path/to/calendly-mcp/server.py"],
"env": {
"CALENDLY_API_TOKEN": "your_actual_token_here"
}
}
}
}
Restart Claude Desktop. You should see "calendly" listed under available tools (hammer icon), and you can ask things like "What meetings do I have this week?" or "Cancel my 3pm tomorrow."
6. Where to go from here
- Add a
reschedule_eventtool (Calendly doesn't have a direct reschedule endpoint — typically you cancel + share a new scheduling link). - Add organization-level tools if you're on a Teams/Enterprise plan
(
/organizations/{uuid}/memberships,/organizations/{uuid}/invitations). - Add webhook support (
/webhook_subscriptions) if you want push notifications instead of polling. - Wrap errors from
resp.raise_for_status()into friendlier messages — right now a bad UUID or expired token will surface as a raw HTTP error.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。