FeedbinMCP

FeedbinMCP

An MCP server that enables users to interact with their Feedbin RSS account directly through Claude. It provides tools for reading articles, managing read and starred states, and browsing subscribed feeds and tags.

Category
访问服务器

README

FeedbinMCP

This project was generated almost entirely by Claude Code, Anthropic's AI coding assistant, with only minor human editing.

An MCP server that connects Claude to your Feedbin RSS account. Read articles, manage read/unread state, and star or unstar entries — all from a Claude conversation.

Tools

Tool Description
get_subscriptions List all subscribed feeds
get_feed Get details for a specific feed
get_unread_entries Paginated unread articles
get_read_entries Paginated read articles
get_starred_entries Paginated starred articles
get_entries Entries with filters (feed, date, IDs)
get_entry Full content for a single entry
get_unread_entry_ids Flat list of all unread IDs
get_starred_entry_ids Flat list of all starred IDs
mark_entries_read Mark one or more entries as read
mark_entries_unread Mark one or more entries as unread
star_entries Star (bookmark) entries
unstar_entries Remove star from entries
get_tags List all tags
get_taggings Feed-to-tag mappings

Requirements

  • Python 3.11+
  • A Feedbin account
  • pip (ships with Python)

Installation

# 1. Clone the repo
git clone https://github.com/hypermoose/FeedbinMCP.git
cd FeedbinMCP

# 2. Install the package and its dependencies
pip install -e .

This installs a feedbin-mcp command and all required dependencies (mcp, httpx).

To confirm the install worked:

feedbin-mcp --help

Adding to Claude Code

Run this once, substituting your real Feedbin credentials:

claude mcp add feedbin \
  --env FEEDBIN_EMAIL=you@example.com \
  --env FEEDBIN_PASSWORD=your_password \
  -- feedbin-mcp

Verify it's registered:

claude mcp list

The server will be available in all Claude Code sessions. Type /mcp inside a session to confirm it's connected.

Credentials

Feedbin uses HTTP Basic Auth (email + password). The server reads credentials from two environment variables:

Variable Description
FEEDBIN_EMAIL Your Feedbin account email
FEEDBIN_PASSWORD Your Feedbin account password

These are passed via --env in the claude mcp add command above and are never stored in the repository.

Running directly (without installing)

If you prefer not to install the package, you can run the server directly with Python after installing dependencies:

pip install mcp[cli] httpx

FEEDBIN_EMAIL=you@example.com \
FEEDBIN_PASSWORD=your_password \
python feedbin_mcp/server.py

And reference it in Claude Code as:

claude mcp add feedbin \
  --env FEEDBIN_EMAIL=you@example.com \
  --env FEEDBIN_PASSWORD=your_password \
  -- python /path/to/FeedbinMCP/feedbin_mcp/server.py

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选