rightcard-mcp
Enables agents to recommend the best credit card for a given store or category, look up merchant coding, search cards, and inspect rotating bonus calendars using verified reward data.
README
RightCard MCP
The card-selection oracle for agents: which of your credit cards should pay here? Answers come from RightCard's bank-published, two-source-verified reward data — the same data the RightCard iOS app uses.
- No bank login. No account. Nothing stored. You pass card ids and a store name; you get an answer.
- Honest by construction: merchant-code caveats (Costco is a warehouse club, so the grocery bonus won't post), rotating quarters with activation flags, ties named, points valued per program.
- Cash value by default;
valuation: "points"for conservative travel values.
Use it
Hosted (stateless Streamable HTTP):
https://mcp.rightcard.ai/mcp
Local (stdio, nothing leaves your machine except a read of the public catalog):
npx rightcard-mcp
Claude Desktop / Claude Code / Cursor config:
{ "mcpServers": { "rightcard": { "command": "npx", "args": ["-y", "rightcard-mcp"] } } }
Tools
| tool | what it answers |
|---|---|
best_card |
which of the given cards earns most at a store or category, today, with caveats |
lookup_merchant |
how a store is coded (category, merchant type, MCC-trap caveat) |
search_cards |
find card ids by name/issuer; verified first, unverified flagged |
card |
one card's verified rates, rotating windows, choose-your-category spec |
rotating_calendar |
live + upcoming rotating windows and permanent merchant benefits |
Try: "I have the Amex Gold, Freedom Flex and Citi Double Cash. Which one at Costco?"
Parity with the app
src/engine.ts is a port of the iOS app's Swift engine. fixtures/engine_golden.json holds
3,100+ answers produced by the Swift code over the real catalog and merchant directory;
npm test fails if the port disagrees on any of them. Offers (a user's personal bank offers)
are deliberately not part of this server — they live on the phone.
Privacy
The hosted server logs request counts only. No identifiers, no cookies, no storage. Full policy: https://rightcard.ai/privacy
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.
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.
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.
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.