Webhook.site MCP Server
Enables LLM agents to create, read, update, and delete Webhook.site tokens, list and retrieve captured requests, and manage webhook configurations via the Webhook.site API.
README
Webhook.site FastMCP
A FastMCP-based Model Context Protocol (MCP) server for the Webhook.site API. It exposes the API as MCP tools for creating, reading, updating, and managing webhook tokens and their captured requests.
Prerequisites
- Python 3.12+
- uv (recommended) or pip
Configuration
Configure the following environment variables to authenticate and set defaults:
| Environment Variable | Description |
|---|---|
WEBHOOK_SITE_API_KEY |
(Optional) Your Webhook.site API key (required for premium accounts, custom actions, and private tokens). |
WEBHOOK_SITE_TOKEN_ID |
(Optional) A default Webhook.site token UUID to fall back to when not explicitly provided to tools. |
Running
Direct execution
uv run server.py
Install editable
You can install this package in editable mode:
uv pip install -e .
This registers the CLI command webhook-mcp.
Claude Desktop example
To use this with Claude Desktop, add the following to your claude_desktop_config.json (usually located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"webhook-mcp": {
"command": "uv",
"args": [
"--directory",
"$HOME/.agents/Webhook.site-FastMCP",
"run",
"server.py"
],
"env": {
"WEBHOOK_SITE_API_KEY": "your-api-key-here",
"WEBHOOK_SITE_TOKEN_ID": "your-default-token-id-here"
}
}
}
}
Available tools
1. create_token
Creates a new Webhook.site token (URL / email address container).
- Arguments:
api_key(string, optional): OverridesWEBHOOK_SITE_API_KEY.default_status(number, optional): Default HTTP status returned to requests (200-599).default_content(string, optional): Default response body content.default_content_type(string, optional): Default response Content-Type (e.g.application/json,text/html).timeout(number, optional): Seconds to sleep before responding (max 30).listen(number, optional): Seconds to wait for "Set Response" endpoint response.expiry(number, optional): Seconds until the token auto-expires (default: 604800, 1 week).request_limit(number, optional): Limits request history stored (0 to 10000).cors(boolean, optional): Iftrue, adds CORS headers to responses.alias(string, optional): Sets a custom token alias.actions(boolean, optional): Enables/disables Custom Actions.clone_from(string, optional): Token UUID to clone settings from.
2. get_token
Get details and configuration of a Webhook.site token.
- Arguments:
token_id(string, optional): Token UUID (defaults toWEBHOOK_SITE_TOKEN_ID).api_key(string, optional): OverridesWEBHOOK_SITE_API_KEY.
3. update_token
Update settings of an existing Webhook.site token.
- Arguments:
- Same configuration parameters as
create_token+token_id.
- Same configuration parameters as
4. delete_token
Delete the Webhook.site token completely.
- Arguments:
token_id(string, optional): Token UUID (defaults toWEBHOOK_SITE_TOKEN_ID).api_key(string, optional): OverridesWEBHOOK_SITE_API_KEY.
5. list_requests
List captured requests, emails, and DNSHooks sent to a token.
- Arguments:
token_id(string, optional): Token UUID.api_key(string, optional): OverridesWEBHOOK_SITE_API_KEY.sorting(string, optional): Sorting order, either"newest"or"oldest".per_page(number, optional): Page size (default: 50, max: 100).page(number, optional): Page number to retrieve (default: 1).date_from(string, optional): Filter requests starting from date (yyyy-MM-dd HH:mm:ss).date_to(string, optional): Filter requests ending at date (yyyy-MM-dd HH:mm:ss).query(string, optional): Query string to filter results.
6. get_latest_request
Get the latest raw request body sent to a Webhook.site token.
- Arguments:
token_id(string, optional): Token UUID.api_key(string, optional): OverridesWEBHOOK_SITE_API_KEY.
7. delete_requests
Delete all or filtered requests captured by a Webhook.site token.
- Arguments:
token_id(string, optional): Token UUID.api_key(string, optional): OverridesWEBHOOK_SITE_API_KEY.date_to(string, optional): Filter to delete requests up to this date.query(string, optional): Filter to delete requests matching this query.
Resources
webhooksite://token/{token_id}/requests
Allows clients to retrieve the complete list of requests captured by the specified token in raw JSON format.
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。