creditkarma-mcp: Instructions file for Claude Code

CLAUDE.md

creditkarma-mcp CLAUDE.md is an instructions file for Claude Code from chrischall/creditkarma-mcp. It costs 7,456 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for creditkarma-mcp, an MCP server that imports Credit Karma transactions into a local SQLite database and provides tools to query them. It documents commands, file layout, tool names, and authentication paths.

In plain words
What is it for?
Developing and reviewing creditkarma-mcp, running its tests and build, handling Credit Karma authentication, and working with transaction-sync and query code.
Why use it?
It gives an AI coding agent the project context needed to work safely in an unfamiliar codebase. This reduces guesswork around building, testing, authentication, and transaction storage.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is chrischall/creditkarma-mcp's own configuration. It tells Claude Code how to work on creditkarma-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything creditkarma-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/creditkarma-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chrischall/creditkarma-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chrischall/creditkarma-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for creditkarma-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrischall/creditkarma-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/creditkarma-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrischall/creditkarma-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/creditkarma-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for creditkarma-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrischall/creditkarma-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/creditkarma-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,456 This file is loaded in full into every session.
When invoked 7,456 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.07456 $0.07456
Opus 5.5 $0.02982 $0.02982
Sonnet 5.5 $0.01491 $0.01491
Haiku 4.5 $0.00746 $0.00746

Measured 3d ago against content hash 89d33763fbd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

creditkarma-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

creditkarma-mcp

MCP server for Credit Karma. Syncs transactions from the Credit Karma GraphQL API into a local SQLite database and exposes query tools via stdio transport.

Commands

npm run build          # Compile TypeScript → dist/
npm test               # Run tests (vitest)
npm run test:watch     # Watch mode
npm run test:coverage  # Coverage report

Run locally (requires built dist):

CK_COOKIES=xxx node dist/index.js

Tool naming

All tools are prefixed ck_ (e.g. ck_sync_transactions, ck_list_transactions).

Architecture

src/
  index.ts              # MCP server entry point — registers all tools, starts stdio transport
  auth.ts               # resolveAuth() + loadAuthIntoClient() — Pattern A three-path priority
  client.ts             # Credit Karma GraphQL client with auto-refresh; OPERATIONS = the balance ops + their app identities
  db.ts                 # SQLite schema, migrations (v2 balances, v3 credit-report matching), upsert helpers
  http.ts               # boundedFetch — the ONE transport (mcp-utils fetchBounded: timeout over the body read, cancellation, 16 MiB cap); names the host on a refused connection; shared USER_AGENT + REQUEST_TIMEOUT_MS
  vault.ts              # Intuit vault (linked-account balances): idxAuth token → POST /v2/search/connections
  creditReport.ts       # Credit-report parsing (getCreditReportHistory → getCreditReport)
  matching.ts           # Pair credit-report rows with the linked accounts they duplicate
  json.ts               # Narrowing helpers for untyped CK / Intuit JSON
  accountId.ts          # Synthesize a stable account id from provider + last-4 (CK returns empty ids)
  queryHash.ts          # Re-read CK's persisted-query hash from its web bundle when the compiled one goes stale
  debug.ts              # CK_DEBUG=1 stderr tracing of auth + refresh (names, JWT timings, redacted bodies — never values)
  transaction.graphql   # Documentation of the GetTransactions fields we read (never sent)
  tools/
    auth.ts             # ck_set_session, ck_forget_session
    healthcheck.ts      # ck_healthcheck — hop report: credential lookup → token validity → refresh → probe
    sync.ts             # ck_sync_transactions
    query.ts            # ck_list_transactions, ck_get_recent_transactions,
                        #   ck_get_spending_by_category, ck_get_spending_by_merchant,
                        #   ck_get_account_summary
    balances.ts         # ck_get_account_balances + refreshBalances() (run once by every sync)
    sql.ts              # ck_query_sql
    hints.ts            # moneyMeta() — `_meta.mint` context-group hints (group `money`; ck_list_transactions is the canonical what's-new read, with view: brief)

Read the full file on GitHub · 165 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · +1 lines · +37 tokens per session 89d33763fbd9
  2. 21d ago Changed · +1 lines · +133 tokens per session 61b3bbd62f09
  3. 24d ago Changed · +4 lines · +832 tokens per session 90f19b62bebf
  4. 29d ago Changed · +127 tokens per session b9df6b9a3cb4
  5. 1mo ago Changed · +12 lines · +1,446 tokens per session 1087ddede24c
  6. 1mo ago Changed · -8 tokens per session 0f128c971782
  7. 1mo ago Changed · +37 tokens per session 5c476d4d7f63
  8. 1mo ago Changed · +2 lines · +717 tokens per session c630a3782b3b
  9. 2mo ago First seen · 145 lines · 4,135 tokens per session scan A aa61da287e4a

Subscribe to this mod's changes

creditkarma-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/creditkarma-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 7,456 tokens to every session, about $0.0298 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

creditkarma-mcp CLAUDE.md compared with instructions from other repositories

creditkarma-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
creditkarma-mcp CLAUDE.mdchrischall/creditkarma-mcpInstructions file13d agoMITA7,456Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot