MCP App Store
by KeenEthics
PointBagel icon

PointBagel

By PointBagel

Get New App Alerts

Overview

PointBagel keeps track of your U.S. credit cards and points, and does the math on them. Connect it and ChatGPT can answer questions about your own wallet: which card earns the most on a purchase, what your points are worth, whether an annual fee is still earning its keep, and which transfer bonuses are live right now. The answers come from your actual cards and spending, priced with PointBagel's verified data on programs, transfer partners, and point values, not from a model's memory. The connection is read-only. ChatGPT can see your cards, balances, and spending, but nothing can move points or money. Point values are estimates, and the answers say so. You'll need a PointBagel account with your cards added. Setup takes a few minutes at pointbagel.com.

Tools

application_eligibility

ChatGPT
The signed-in user's credit-card application posture, read from their own card history only: how many new cards they have opened in the last 24 months, which issuers they are at an application limit with, and counts of the once-per-lifetime bonuses already taken, the bonus cooldowns still running, and the product conflicts in the way. It can also assess a specific card they name, including when a blocking rule clears, or a ranked shortlist of cards they could apply for next drawn from their own spending. Reflects the issuer eligibility rules PointBagel verifies; it never predicts approval odds and holds no credit-score, income, or SSN data. Read-only.

best_redemption

ChatGPT
For ONE of the signed-in user's points programs: the estimated value of their balance and the valuation basis behind that estimate, the transfer partners with their current ratios, the sweet-spot awards worth aiming for and how far the balance goes toward each, and which card would unlock full transfer access. Point values are estimates from PointBagel's verified benchmarks, not promised redemption values. Does NOT check live award availability; for open award seats use point.me, Seats.aero, or the airline. Read-only; the user's own balances only.

card_detail

ChatGPT
One credit card in detail, set against the rest of the signed-in user's wallet. This is the tool for any question about the user's OWN card, including one they closed or converted: it reports whether they hold it now, held it before (with the card it became or came from), or never had it. For a held card: its earning structure, its statement credits by name with how much of each has been used, a personalized fee verdict once the card is tracked, and a lifetime scorecard of fees against benefits captured. Falls back to catalog facts only when the user has no history with the card. Pass a card name or catalog id. Values are estimates.

card_facts

ChatGPT
Published facts for ANY credit card in PointBagel's verified catalog: the card's earn rates by category, annual fee, the statement credits it carries by name, the current public welcome offer, and a link to apply. Works with no wallet connected. Use it for questions about a card in general, like what a card earns at restaurants, which credits come with it, or whether it has an offer right now. For questions about the user's own cards - including a card they closed or converted - use card_detail instead; this tool knows nothing about who holds what. Facts are verified against issuer terms; estimates, not guarantees. Read-only.

card_impact

ChatGPT
Estimate how adding a candidate card would change the signed-in user's annual rewards: the ongoing per-year value change (extra earn minus extra fees), which spending categories would move to the new card, the wallet's total annual earn before and after, and the one-time welcome offer kept separate from the recurring math. Modeled against the user's own tracked spending over the last 12 months. Values are estimates, never approval predictions. This tool is part of the PLUS plan.

fee_verdict

ChatGPT
Assess whether one card in the signed-in PointBagel user's own wallet is still worth its annual fee, and what to do about it: the keep-or-cancel recommendation, the ROI, the benefit value actually captured, and the credits left unused, for the current membership year or a completed past year (period). Read-only and owned-scope. Requires the card to be tracked; untracked cards return catalog facts plus how to unlock the verdict. Values are estimates.

portfolio_summary

ChatGPT
Summarize the signed-in PointBagel user's own wallet and how well it is working for them: points balances with their estimated value, the cards in the wallet that carry an annual fee, with the fee and when it is due, statement credits about to expire, and rollups of what the wallet costs and how much of its value is being captured across the cards PointBagel can score. Read-only; this user's own cards and programs only, never another person's. Values are estimates. Optional include narrows the answer to one block.

transfer_bonuses

ChatGPT
Transfer-bonus coverage across the programs PointBagel tracks: the bonuses live right now and, optionally, the ones announced to start soon, with source and destination program, the standard and boosted ratios, any cap on the bonus portion, the start and end dates, whether registration is required first, and whether the user holds the source currency. Bonus ratios are shown as a range when they vary by status tier or by card, never as a single number. Does NOT check live award availability. Read-only.

welcome_offer

ChatGPT
Welcome-offer coverage for one credit card: the current published offer (bonus, minimum spend, time window, and when PointBagel verified it), a verified finding when a card has no public offer, and, for a card the user owns, their estimated progress toward the bonus from imported transactions. Use it to judge how strong an offer is and whether to apply now or wait. Estimates, not guarantees. Read-only.

which_card

ChatGPT
Recommend which of the signed-in user's own credit cards to use for a given store or spending category, and show the earning behind the call: the effective earn rate, which already reflects how much of that category cap the user has spent this period, the estimated value per dollar, the runner-up cards in their wallet, and any welcome-bonus spend in progress. Assumes a small default purchase when no amount is given. Values are estimates. Read-only; the user's own wallet only.

which_card_for_named_cards

ChatGPT
Recommend which credit card to use for a store or spending category from the cards the user names in the conversation, including cards they have not saved to PointBagel yet. Each named card is priced from PointBagel's verified catalog: the earn rate, the estimated value per dollar, and the runner-up cards. Spending caps are treated as unspent, and a rotating quarterly bonus that needs activation counts only for a card the user says they activated this quarter. Asks which card was meant when a name matches more than one, marks cards already saved to this account, and says how to save the rest. For cards already saved, which_card answers from the user's own spending and caps instead. Values are estimates. Read-only.

Example Prompts

Click any prompt to copy it.

Similar Apps