AgentFeed MCP server
Commit Oct 29, 2026Converts RSS/Atom feeds into clean JSON and extracts article text or markdown from any web URL for AI agents.
Also known as wminno/agentfeed
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.4.3
- Last commit
- Oct 29, 2026
- License
- MIT
What is AgentFeed MCP?
AgentFeed converts RSS/Atom feeds into clean JSON and extracts article text or markdown from any web URL for AI agents.
Summary generated from the project's README
About AgentFeed MCP server
Transforming RSS and Atom feeds into structured JSON or converting web pages into clean markdown is what AgentFeed enables for AI developers. By connecting an MCP client like Claude Desktop or an IDE to the remote server, you can provide agents with high-quality content without manual scraping. The server provides two primary tools: fetch_feed for turning feeds into predictable JSON arrays and fetch_article for extracting text or markdown from specific URLs.
Users can access the service via a streamable-HTTP connection by pointing their client to the hosted endpoint and providing an API key through the X-Api-Key header. The system includes built-in safety limits, such as a 2 MB and 15 second cap on outbound fetches to prevent issues. While a free tier allows 30 requests per minute per IP without a key, a paid tier is available for higher volume needs. The architecture is stateless and lightweight, making it easy to host your own instance locally using a simple Python setup.
What you can do with it
- 1Automated news monitoringAsk an AI agent to monitor an RSS feed and summarize the latest headlines.
- 2Web content extractionHave an agent read the full text of a specific blog post to answer questions.
- 3Structured data ingestionProvide an AI with predictable JSON data containing titles, links, and summaries from a feed.
Written from the project's README. Every use case is checked against a quote from it.
How to install AgentFeed MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall AgentFeed MCP in Claude Code
$ claude mcp add --transport http agentfeed https://agentfeed.bigfloppy.net/mcpInstall AgentFeed MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentfeed": {
"url": "https://agentfeed.bigfloppy.net/mcp"
}
}
}Install AgentFeed MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentfeed": {
"type": "http",
"url": "https://agentfeed.bigfloppy.net/mcp"
}
}
}Install AgentFeed MCP in VS Code CLI
$ code --add-mcp '{"name":"agentfeed","type":"http","url":"https://agentfeed.bigfloppy.net/mcp"}'Install AgentFeed MCP in Codex
$ codex mcp add agentfeed --url https://agentfeed.bigfloppy.net/mcpInstall AgentFeed MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentfeed] url = "https://agentfeed.bigfloppy.net/mcp"
Install AgentFeed MCP in Gemini CLI
$ gemini mcp add -s user --transport http agentfeed https://agentfeed.bigfloppy.net/mcpInstall AgentFeed MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentfeed": {
"url": "https://agentfeed.bigfloppy.net/mcp",
"type": "http"
}
}
}README
View on GitHubAgentFeed — tiny content-extraction API for AI agents
One GET request turns any RSS/Atom feed into clean JSON, or any web page into
clean text/markdown. No SDK, no signup, no tracking. A live instance runs at
https://agentfeed.bigfloppy.net.
MCP (Model Context Protocol)
POST /mcp is a streamable-HTTP MCP server exposing the same pipeline as two tools: fetch_feed (RSS/Atom -> JSON) and fetch_article (page -> text/Markdown). Point any MCP client (Claude Desktop, IDEs, agent frameworks) at https://agentfeed.bigfloppy.net/mcp; pass your API key via the X-Api-Key header. Same quotas and pricing as the REST API.
Endpoints
GET /api/feed?url=<rss-or-atom-url> # feed -> {title, link, published, summary}[]
GET /api/article?url=<page-url> # page -> {title, author, text, markdown}
GET /api/health
curl 'https://agentfeed.bigfloppy.net/api/feed?url=https://hnrss.org/frontpage'
curl 'https://agentfeed.bigfloppy.net/api/article?url=https://blog.python.org/'
Features
- Agent-friendly JSON — flat, predictable shapes; summaries truncated to 500 chars, article text capped at 20k chars.
- Fair free tier — 30 requests/min per IP, no key needed. Paid key: $5 per 100k requests/year (card, Stripe checkout, or USDC on Base with on-chain self-verification — no email, no accounts).
- SSRF-safe outbound fetch — 2 MB / 15 s caps, gzip handled.
- Single process, stdlib server — SQLite-free, stateless; only a small JSON file for key state.
Run your own
pip install -r requirements.txt
python3 server.py # serves on :5000
Edit paid.py to set your own wallet address and Stripe codes, or ignore that
file's payment logic entirely — the API works without keys on the free tier.
License
MIT — see LICENSE.
AgentFeed MCP questions
How do I add AgentFeed MCP to Claude Code?
Run claude mcp add --transport http agentfeed https://agentfeed.bigfloppy.net/mcp in your terminal. Add --scope user to make it available in every project.
How do I add AgentFeed MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Is there a free tier available?
Yes, there is a fair free tier that allows 30 requests per minute per IP without requiring an API key.
What are the limits on article text length?
Article text is capped at 20,000 characters and summaries are truncated to 500 characters.