Koko MCP Server

A hosted MCP server for AI-powered credit card advice. Search 100+ US credit cards, compare options side by side, analyze portfolio health, and get

Remote serverstreamable-httpGo

What is the Koko MCP server?

A hosted MCP server for AI-powered credit card advice. Search 100+ US credit cards, compare options side by side, analyze portfolio health, and get personalized recommendations — all through the Model Context Protocol. That is what the koko mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • search_credit_cards — Natural language search across 100+ US credit cards. Optional filters: card_type, issuer, max_annual_fee, credit_tier
  • compare_cards — Side-by-side comparison of 2-3 cards with fees, rewards, net value, and break-even. Optional: credit_tier, primary_goal, issuer_preferences (<100ms)
  • get_card_details — Full details for a specific card (fees, rewards, benefits)
  • calculate_card_value — Annual fee break-even analysis with first-year and ongoing value
  • optimize_portfolio — Portfolio health score, per-card KEEP/OPTIMIZE/CANCEL verdicts. Optional: point_balances, benefit_selections, credit_tier, primary_goal
  • recommend_card_for_category — Best card to use for a specific spending category, ranked by reward value. Optional: spending, credit_tier, primary_goal, issuer_preferences (<100ms)
  • check_card_renewal — Should you renew this card? Verdict + downgrade/replacement options. Optional: benefit_selections, acquired_date, credit_tier, primary_goal
  • create_mcp_session — Session tracking for multi-query conversations
  • which_card_at_merchant — Best card from your portfolio at a specific merchant. Auto-detects spending category (e.g. Starbucks → dining) and ranks by reward value
  • check_merchant_benefits — Check if any cards have credits at a merchant (e.g. Saks → Amex Platinum $100 credit). Includes earning recommendation
  • get_card_benefits — All credits/benefits for a card with value, frequency, schedule, and conditions
  • get_card_terms — Schumer Box data — purchase APR, penalty APR, late fees, cash advance fees, promotional APR, grace period

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Koko's toolset — search_credit_cards, compare_cards, get_card_details and 11 more — is a fair guide to whether it matches your workflow. It is maintained by madanc; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Koko's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Koko.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_credit_cardsNatural language search across 100+ US credit cards. Optional filters: card_type, issuer, max_annual_fee, credit_tier
compare_cardsSide-by-side comparison of 2-3 cards with fees, rewards, net value, and break-even. Optional: credit_tier, primary_goal, issuer_preferences (<100ms)
get_card_detailsFull details for a specific card (fees, rewards, benefits)
calculate_card_valueAnnual fee break-even analysis with first-year and ongoing value
optimize_portfolioPortfolio health score, per-card KEEP/OPTIMIZE/CANCEL verdicts. Optional: point_balances, benefit_selections, credit_tier, primary_goal, issuer_preferences, analysis_type, cancel_threshold, keep_threshold (<100ms)
recommend_card_for_categoryBest card to use for a specific spending category, ranked by reward value. Optional: spending, credit_tier, primary_goal, issuer_preferences (<100ms)
check_card_renewalShould you renew this card? Verdict + downgrade/replacement options. Optional: benefit_selections, acquired_date, credit_tier, primary_goal, renewal_cancel_threshold, renewal_keep_threshold
create_mcp_sessionSession tracking for multi-query conversations
which_card_at_merchantBest card from your portfolio at a specific merchant. Auto-detects spending category (e.g. Starbucks → dining) and ranks by reward value
check_merchant_benefitsCheck if any cards have credits at a merchant (e.g. Saks → Amex Platinum $100 credit). Includes earning recommendation
get_card_benefitsAll credits/benefits for a card with value, frequency, schedule, and conditions
get_card_termsSchumer Box data — purchase APR, penalty APR, late fees, cash advance fees, promotional APR, grace period
get_card_changesAudit log of card data changes (fee updates, benefit changes) with date filtering. Optional: field filter
get_program_trendsPoints program valuation history — CPP and transfer partner ratio changes over time

How to install the Koko MCP server

{
  "mcpServers": {
    "koko-finance": {
      "type": "http",
      "url": "https://kokofinance.net/mcp/"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Koko to search credit cards.
  • Use Koko to compare cards.
  • Use Koko to get card details.

Frequently asked questions

It connects Koko to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (search_credit_cards, compare_cards, get_card_details, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Koko directly.