creditkarma-mcp

MCP server for Credit Karma — syncs transactions into a local SQLite database and provides natural-language querying tools.

• npm: npmjs.com/package/creditkarma-mcp
• Source: github.com/chrischall/creditkarma-mcp

Setup

Option A — npx (recommended)

Add to .mcp.json in your project or ~/.claude/mcp.json:

{
  "mcpServers": {
    "creditkarma": {
      "command": "npx",
      "args": ["-y", "creditkarma-mcp"],
      "env": {
        "CK_COOKIES": "CKTRKID=...; CKAT=eyJ...%3BeyJ...; ..."
      }
    }
  }
}

Option B — from source

git clone https://github.com/chrischall/creditkarma-mcp
cd creditkarma-mcp
npm install && npm run build

Then add to .mcp.json:

{
  "mcpServers": {
    "creditkarma": {
      "command": "node",
      "args": ["/path/to/creditkarma-mcp/dist/index.js"],
      "env": {
        "CK_COOKIES": "CKTRKID=...; CKAT=eyJ...%3BeyJ...; ..."
      }
    }
  }
}

Or use a .env file in the project directory with CK_COOKIES=<value>.

Getting CK_COOKIES

Scripted (recommended — source install):

npm run auth               # prints the Cookie header to the console
npm run auth -- .env       # writes CK_COOKIES=<header> to .env

Launches Chrome with a dedicated profile, waits for sign-in at creditkarma.com, then captures the full session Cookie header (CKAT carries the access + refresh JWTs; CKTRKID and friends are needed by the refresh endpoint). Use the printed value with Claude Desktop / MCPB, or the .env form when running from source.

Manual (DevTools):

1. Log in to creditkarma.com in Chrome
2. DevTools → Network → any creditkarma.com request → Request Headers
3. Right-click the cookie header → Copy value

Authentication

Call ck_set_session with your Cookie header to store credentials and enable auto-refresh.

• Access token: ~15 min TTL, auto-refreshed transparently
• Refresh token: ~8 hours TTL
• When expired: re-run npm run auth (or grab a fresh Cookie header) and call ck_set_session

Tools

Auth

Tool	Description
ck_set_session(cookies)	Store credentials — paste the full Cookie header from a signed-in creditkarma.com request

Sync

Tool	Description
ck_sync_transactions(force_full?)	Sync transactions to local SQLite. Incremental by default (since last sync − 30 days). force_full=true re-fetches everything.

Query

Tool	Description
ck_list_transactions(start_date?, end_date?, account?, category?, merchant?, status?, min_amount?, max_amount?, limit?, offset?)	Filtered, paginated transaction list
ck_get_recent_transactions(limit?)	N most recent transactions (default 20)
ck_get_spending_by_category(start_date?, end_date?)	Spending totals grouped by category
ck_get_spending_by_merchant(start_date?, end_date?, limit?)	Spending totals grouped by merchant
ck_get_account_summary	Transaction counts and totals per account
ck_query_sql(sql)	Read-only SQL query against the local database (SELECT only)

Workflows

First-time setup:

1. Run npm run auth (or grab the Cookie header manually from a creditkarma.com request in DevTools)
2. Paste into CK_COOKIES env var, or call ck_set_session(cookies) from within Claude
3. ck_sync_transactions → initial full sync

Regular use:

• ck_sync_transactions → pull latest transactions
• Then query with any of the query tools

Spending analysis:

ck_sync_transactions
ck_get_spending_by_category(start_date: "2026-01-01", end_date: "2026-03-31")
ck_get_spending_by_merchant(start_date: "2026-01-01", limit: 10)

Custom analysis with SQL:

-- Monthly spending totals
SELECT strftime('%Y-%m', date) AS month, SUM(ABS(amount)) AS total
FROM transactions WHERE amount < 0
GROUP BY month ORDER BY month DESC

-- Spending by category this year
SELECT c.name, SUM(ABS(t.amount)) AS total
FROM transactions t JOIN categories c ON t.category_id = c.id
WHERE t.date >= '2026-01-01' AND t.amount < 0
GROUP BY c.name ORDER BY total DESC

Database schema

transactions (id, date, description, status, amount, account_id, category_id, merchant_id, raw_json)
accounts     (id, name, type, provider_name, display)
categories   (id, name, type)
merchants    (id, name)
sync_state   (key, value)

Notes

• All query tools run against the local SQLite database — sync first
• Amounts: negative = expense/debit, positive = credit/income
• ck_query_sql only allows SELECT — no writes to Credit Karma data
• Sync saves a resume cursor — interrupted syncs can be resumed automatically
• accounts.id is a synthesized stable key in the form <provider>|<last4> (e.g. Citi|2630, Ally|7133) because CK's API returns empty account.id strings. The same card under two provider-name spellings shows as two rows.