pointmaxx-mcp
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
pointmaxx-mcp
Ask your AI assistant which credit card to use, and which cards would earn you the most, with the same math as pointmaxx.app. Compares 53 U.S. credit cards after annual fees, spending caps and the credits you'd actually use.
Set it up
Claude Desktop: open Settings, then Developer, then Edit Config, add this, and restart Claude:
{
"mcpServers": {
"pointmaxx": { "command": "npx", "args": ["-y", "pointmaxx-mcp"] }
}
}Any other MCP app: run npx -y pointmaxx-mcp as a stdio server. Needs Node 18 or later.
Related MCP server: GetCurrentOffer MCP Server
What you can ask
Tool | Ask your assistant something like |
| "I have Amex Gold and Citi Double Cash. Which should I use on DoorDash?" |
| "I spend about $500 a month on groceries, $300 on dining and $1,500 on everything else. Which two cards would earn the most? I have a Double Cash." |
| "What's the annual fee on the Sapphire Reserve, and what are its credits?" |
Answers include each card's percent back, why it wins, any spending cap, the net value a year after fees, and how much more that is than the cards you already have.
Privacy
It runs on your own computer and makes no network requests. It only needs card names and rough monthly spending by category: never statements, card numbers or a login. Nothing is saved.
Good to know
Estimates from each card's published terms, checked against issuer pages. Not financial advice; check the issuer before you apply.
Points are valued at a fixed cents-per-point for each card. Sign-up bonuses are left out.
Card terms are built into each release. Run with
npx -y pointmaxx-mcpto always get the latest.
For a full backtest on a year of your own statements, read in your browser and never uploaded, try pointmaxx.app.
MIT licensed. Card data includes CardPin (MIT).
Source
This repo is the published package: server.mjs plus the engine and card data in lib/, copied from PointMaxx's main codebase at each release. Run npm test to check it.
This server cannot be deployed
Maintenance
Related MCP Connectors
AI credit card advisor - search cards, compare portfolios, and optimize rewards
Ask Claude or ChatGPT about your own credit cards: best card to use, utilization, missed rewards.
Search, compare and estimate rewards across US credit cards. Verified fees, APRs and bonuses.
US credit card data: annual fees, credit card credits, earn rates, offers and cashback portal rates.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides tools to fetch and analyze credit card data with filtering options for banks, categories, and user personas. It also offers access to educational guides to assist in making informed financial recommendations.-
- FlicenseNot gradedqualityDmaintenanceEnables searching and comparing live credit card merchant offers (cash back, points, statement credits) across Amex, Chase, Citi, PayPal, Rakuten, and Capital One from any AI agent.-
- AlicenseAqualityCmaintenanceEnables 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.51,195 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables users to search and compare credit card recommendations, view card details and popular top-5 cards, and retrieve financial knowledge articles through MCP tools.-