rfd-mcp
MCP server for searching and monitoring RedFlagDeals deals. Provides tools to search deals, get deal details, and set up monitors for new deals.
README
rfd-mcp
rfd-mcp is a standalone local stdio MCP server for searching and monitoring RedFlagDeals topics.
It has no source or package dependency on the RFD frontend repository. It references RFD only through the cached JSON feed configured with RFD_TOPICS_URL or RFD_TOPICS_FILE. By default it reads the deployed rfd-fyi feed at:
https://github.com/carteakey/rfd
The default data endpoint is:
https://rfd-fyi.pages.dev/topics.json
For local development, set RFD_TOPICS_FILE to a JSON file or set RFD_TOPICS_URL to a local Pages/Wrangler endpoint.
Install and build
From this repository root:
npm ci
npm run build
The compiled server is dist/index.js.
Configure an MCP client
For Claude Code:
claude mcp add rfd -- node /absolute/path/to/rfd-mcp/dist/index.js
Or add an entry like this to an MCP client configuration. The environment variables are optional.
{
"mcpServers": {
"rfd": {
"command": "node",
"args": ["/absolute/path/to/rfd-mcp/dist/index.js"],
"env": {
"RFD_TOPICS_URL": "https://rfd-fyi.pages.dev/topics.json",
"RFD_MCP_DATA_DIR": "/absolute/path/to/rfd-mcp-data"
}
}
}
}
Tools
search_dealssearches topic titles and retailer names. It supports additional filter chips,/regular expression/filters, retailer filtering, score bounds, the same six sort keys as the frontend, and a result limit.get_dealreturns the complete cached topic record plus the forum and direct-offer links for atopic_id.monitor_searchsaves a search and keeps the latest 500 seen topic IDs.check_monitorschecks one or all saved searches and returns only unseen deals.list_monitorslists saved searches and their last-check state.delete_monitorremoves a saved search.
RFD's cached topic schema does not contain Marketplace-style location, price, or category fields. Those filters are intentionally not exposed; the server uses the fields the RFD scraper actually stores.
Configuration
| Variable | Default | Purpose |
|---|---|---|
RFD_TOPICS_URL |
https://rfd-fyi.pages.dev/topics.json |
Cached topics endpoint |
RFD_TOPICS_FILE |
unset | Read topics from a local JSON file instead of HTTP |
RFD_FORUM_BASE_URL |
https://forums.redflagdeals.com |
Base URL for thread links |
RFD_MCP_CACHE_TTL_MS |
30000 |
In-memory topics cache lifetime |
RFD_MCP_DATA_DIR |
~/.rfd-mcp |
Directory for monitor state |
RFD_MCP_MONITORS_FILE |
$RFD_MCP_DATA_DIR/monitors.json |
Exact monitor state path |
Tests
npm test
npm run build
The server uses MCP stdio transport, so stdout is reserved for protocol traffic. Diagnostics are returned as tool errors or written by dependencies to stderr.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.