KoKo Finance 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.

Server URL: https://kokofinance.net/mcp/

No API key required. No local installation needed. Just connect your MCP client.

Quick Setup

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

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

Claude Code

claude mcp add koko-finance --transport http https://kokofinance.net/mcp/

Or copy the .mcp.json from this repo into your project.

Cursor

Go to Settings > MCP and add a new server:

• Name: koko-finance

• Type: HTTP

• URL: https://kokofinance.net/mcp/

Cline / Windsurf

Add to your MCP settings file:

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

Related MCP server: Discovery Engine MCP Server

Tools (14)

Personalization Parameters

Several tools accept optional parameters that improve result relevance. All are optional — when omitted, the server uses sensible defaults (e.g., national average spending, no issuer bias).

credit_tier

Credit score range that affects card eligibility and approval likelihood.

Used by: search_credit_cards, compare_cards, optimize_portfolio, recommend_card_for_category, check_card_renewal

primary_goal

The user's main objective for their credit card strategy.

Used by: compare_cards, optimize_portfolio, recommend_card_for_category, check_card_renewal

issuer_preferences

A list of issuer preference objects that express affinity or aversion toward specific card issuers. Each entry has an issuer name and a weight between -1.0 (strong aversion) and 1.0 (strong preference).

[
  {"issuer": "Chase", "weight": 0.8},
  {"issuer": "American Express", "weight": 0.5},
  {"issuer": "Capital One", "weight": -0.5}
]

Used by: compare_cards, optimize_portfolio, recommend_card_for_category

spending

A dictionary of monthly spending amounts by category, used to calculate personalized reward values instead of national averages.

{"dining": 500, "groceries": 800, "travel": 300, "gas": 150, "general": 2000}

Used by: compare_cards, optimize_portfolio, recommend_card_for_category, check_card_renewal, calculate_card_value

cancel_threshold / keep_threshold

Override the default net-value thresholds (in dollars) for KEEP/OPTIMIZE/CANCEL verdicts.

• cancel_threshold — Cards below this → CANCEL (default: -50)

• keep_threshold — Cards above this → KEEP (default: 50)

Used by: optimize_portfolio

renewal_cancel_threshold / renewal_keep_threshold

Same concept applied to a single card's renewal decision.

Used by: check_card_renewal

acquired_date

Date the user acquired the card (YYYY-MM-DD). Informs tenure-based renewal analysis.

Used by: check_card_renewal

Response Metadata

Calculation tools include metadata fields in responses:

• spending_source — "user_provided" or "national_averages". Indicates whether calculations used user-supplied spending or BLS national averages.

• data_source — Indicates where card data was sourced (e.g., "koko_db").

• rewards_by_category — Per-category reward breakdown included in compare, portfolio, and value tools.

• points_program_key / portal_cpp — Points program identifier and portal cents-per-point valuation, included on all card data.

Prompts (5)

Pre-built conversation starters that guide the AI through structured workflows:

Benefit Selections

The optimize_portfolio and check_card_renewal tools accept a benefit_selections parameter — a list of individual benefit keys the user actually uses. Selected benefits count at 100% utilization; unselected benefits count at 0%.

benefit_selections: ["uber", "airline_fee", "dining", "admirals_club"]

This gives accurate net-value calculations instead of the default 50% utilization estimate.

Discover valid keys by calling the REST endpoint GET https://kokofinance.net/api/v1/benefit-categories (no auth required), or see the developer docs.

Example Conversations

"Review my portfolio"

I have a Chase Sapphire Reserve, Amex Gold, and Citi Double Cash. Analyze my portfolio and tell me which cards are worth keeping.

"Which card should I use?"

I'm buying $200 in groceries. I have an Amex Gold, Chase Freedom Unlimited, and Citi Custom Cash. Which card should I use?

"Find me a new card"

I spend a lot on travel and dining. I want a card under $300 annual fee with a good sign-up bonus. What do you recommend?

"Should I renew my Amex Platinum?"

I only use the Uber credit and airline fee credit on my Amex Platinum. Is it still worth paying the $695 annual fee?

"Which card at Starbucks?"

I'm buying coffee at Starbucks. I have a Chase Sapphire Reserve, Amex Gold, and Citi Double Cash. Which card earns the most?

"Do I have any credits at Saks?"

I'm shopping at Saks Fifth Avenue. Do any of my cards have credits there? I have an Amex Platinum and Chase Sapphire Reserve.

"What benefits does my Amex Platinum have?"

Show me all the credits and benefits on my Amex Platinum card — how much is each worth?

Screenshots

Screenshots captured from Claude using the KoKo Finance MCP server.

1. Search for Credit Cards

"Find me the best travel credit cards under $300 annual fee"

2. Compare Cards Side by Side

"Compare Chase Sapphire Reserve and Amex Gold"

3. Portfolio Review

"Analyze my portfolio: Chase Sapphire Reserve, Amex Gold, Citi Double Cash"

4. Which Card at a Merchant

"Which card should I use at Starbucks?"

5. Card Benefits Breakdown

"Show me all the credits and benefits on my Amex Platinum"

Links

• KoKo Finance — Main site

• Developer Documentation — Full API and tool reference

• MCP Endpoint — Direct server URL

Also Available

• Claude Code Plugin — Adds the MCP server connection plus an Agent Skill that teaches Claude structured credit card workflows

Privacy Policy

KoKo Finance collects minimal data required to operate the MCP server:

• Authentication data: Google OAuth profile (name, email) when you sign in. No sign-in is required for free-tier usage.

• Usage logs: Tool name, parameters, success/failure status, and timestamp for each MCP tool call. Used for rate limiting and service improvement.

• No third-party sharing: We do not sell or share personal data with third parties.

• Data retention: Usage logs are retained for service operation. You can request deletion by contacting us.

• Contact: privacy@kokofinance.net

Full privacy policy: https://kokofinance.net/privacy.html

License

MIT