FreshRSS Agent
MCP server for FreshRSS RSS reader enabling feed reading, subscription management, and item actions via the Google Reader compatible API.
README
FreshRSS
CLI or API | MCP | Agent
Version: 0.1.0
Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, the integrated A2A agent server, and guidance for provisioning the backing platform are maintained in the official documentation.
Table of Contents
Overview
FreshRSS MCP Server + A2A Agent
A connector for the self-hosted FreshRSS RSS reader, wrapping its Google Reader compatible API (GReader). It exposes two action-routed MCP tool domains:
freshrss_reader—stream_contents(feed items + continuation),item_contents,unread_count.freshrss_subscriptions—list,subscribe,unsubscribe,label,categories,mark_read,star.
This repository is actively maintained - Contributions are welcome!
Key Features
- Consolidated Action-Routed MCP Tools: Two togglable tool domains group every GReader operation, minimizing token overhead and tool bloat in LLM contexts.
- Google Reader Compatible: Wraps the FreshRSS GReader API —
ClientLoginauth, transparent re-authentication on401, and automatic write-token handling. - Enterprise-Grade Security: OIDC token delegation (RFC 8693), Eunomia policy enforcement, and per-instance credential resolution.
- Integrated A2A Agent: Built-in Pydantic AI agent server alongside the MCP server.
- Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and Langfuse tracing.
MCP
Available MCP Tools
This server uses dynamic Action-Routed tools to optimize token overhead and maximize
IDE compatibility. Each tool takes an action plus a params_json payload.
| Tool Module | Toggle Env Var | Enabled by Default | Description & Action-Routed Methods |
|---|---|---|---|
| Reader | READERTOOL |
True |
Read FreshRSS streams via the GReader API. Action-routed methods: stream_contents, item_contents, unread_count. |
| Subscriptions | SUBSCRIPTIONSTOOL |
True |
Curate feeds, categories, and item tags. Action-routed methods: list, subscribe, unsubscribe, label, categories, mark_read, star. |
Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/usage.md.
Environment Variables
The MCP Server can be run in stdio (local), streamable-http (networked), or
sse mode.
FRESHRSS_URL: The base URL of the FreshRSS instance (e.g.http://freshrss.arpa).FRESHRSS_USER: The FreshRSS username (GReaderEmailfield).FRESHRSS_API_PASSWORD: The FreshRSS API password (Settings → Authentication).FRESHRSS_SSL_VERIFY: Whether to verify TLS certificates (defaultTrue).
stdio Transport (local IDEs - Cursor, Claude Desktop, VS Code)
{
"mcpServers": {
"freshrss-mcp": {
"command": "uvx",
"args": ["--from", "freshrss-agent", "freshrss-mcp"],
"env": {
"FRESHRSS_URL": "https://service.example.com",
"FRESHRSS_USER": "admin",
"FRESHRSS_API_PASSWORD": "your_api_password"
}
}
}
}
Streamable-HTTP Transport (networked / production)
{
"mcpServers": {
"freshrss-mcp": {
"command": "uvx",
"args": ["--from", "freshrss-agent", "freshrss-mcp", "--transport", "streamable-http", "--port", "8000"],
"env": {
"TRANSPORT": "streamable-http",
"HOST": "0.0.0.0",
"PORT": "8000",
"FRESHRSS_URL": "https://service.example.com",
"FRESHRSS_USER": "admin",
"FRESHRSS_API_PASSWORD": "your_api_password"
}
}
}
}
<!-- BEGIN GENERATED: additional-deployment-options -->
Additional Deployment Options
freshrss-agent can also run as a local container (Docker / Podman / uv) or be
consumed from a remote deployment. The
Deployment guide has full,
copy-paste mcp_config.json for all four transports — stdio, streamable-http,
local container / uv, and remote URL:
- Local container / uv — launch the server from
mcp_config.jsonviauvx,docker run, orpodman run, or point at a local streamable-http container byurl. - Remote URL — connect to a server deployed behind Caddy at
http://freshrss-mcp.arpa/mcpusing the"url"key. <!-- END GENERATED: additional-deployment-options -->
Usage
Once configured, an LLM (or a direct caller) invokes a tool domain with an action
and a JSON params_json payload. Examples:
// Fetch the 50 most recent unread items, newest first
{
"tool": "freshrss_reader",
"action": "stream_contents",
"params_json": "{\"count\": 50, \"order\": \"n\"}"
}
// Subscribe to a feed and file it under a category
{
"tool": "freshrss_subscriptions",
"action": "subscribe",
"params_json": "{\"feed_url\": \"http://example.com/rss\", \"category\": \"News\"}"
}
// Mark items as read
{
"tool": "freshrss_subscriptions",
"action": "mark_read",
"params_json": "{\"item_ids\": [\"tag:google.com,2005:reader/item/0001\"]}"
}
Invoking a tool with an unknown or omitted action returns the discovery payload
listing every valid action for that domain.
Installation
# Using uv (recommended)
uv pip install freshrss-agent
# Using standard pip
python -m pip install freshrss-agent
After installation two console scripts are available:
freshrss-mcp # run the MCP server
freshrss-agent # run the A2A agent server
Documentation
Full installation, deployment, usage, and platform-provisioning guides live in the
docs/ directory and are published via mkdocs + GitHub Pages at the
official documentation site:
- Overview · Installation · Usage · Deployment · Platform · Concepts
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。