Ledger MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Ledger MCP
Ask an AI assistant about card fraud, and let it check the answers in the data.
An MCP server for Ledger, my project on a year of card payments at Meridian Bank, a made-up Portuguese bank: 430,000 payments, three kinds of planted fraud, and six SQL checks that score every payment.
With this server, Claude (or any MCP client) can:
answer questions about the data: "Which country do stolen cards get used in most?"
explain a decision: "Why was payment 406064 blocked? Was it really fraud?"
find the mistakes: "Show me the biggest frauds the checks missed."
try changes before making them: "What if we block at 50 points instead of 60?"
It doesn't copy anything from Ledger. It imports the ledger package from a Ledger checkout, so the checks, scoring and points system are the same code that builds the report.
Tools
Tool | What it does |
| Headline numbers: customers, payments, money spent, fraud losses, thresholds |
| Tables, columns, row counts and the commented schema |
| The 10 ready-made SQL analyses behind the report (category mix, contactless trend, fraud hotspots, time to report, ...) |
| Any read-only |
| The six checks in plain words, with their points, settings and SQL |
| Precision, recall and euros caught, for each check and for the combined points system |
| Re-run one check with one setting changed and compare (e.g. R1 |
| Change the review/block thresholds and see fraud caught vs genuine customers stopped |
| One payment in full: shop, card, customer, checks tripped with evidence, score, decision, and whether it really was fraud |
| A card's payments in order, optionally around one payment (to spot test charges or a trip abroad) |
| Example payments by outcome: |
It also has two resources (ledger://schema, ledger://checks) and two prompts (investigate_payment, tune_the_checks).
Every tool is read-only. The database is opened with SQLite's mode=ro. query_sql also uses an authorizer that only allows reads, so writes, ATTACH, PRAGMA and extension loading are refused even if they get past the single-statement check. The what-if tools change settings for that call only and save nothing.
Related MCP server: Company Data MCP Server
Example
You: Why was payment 406064 stopped?
Claude (calls
explain_payment, thencard_activity): It was a €1,495 online purchase at an electronics shop at 4:53 in the morning, on the debit card of a customer aged 65+ from Lisboa. Two checks fired. Unusually big payment (+30): it was 14.4× this card's usual €103.90. Late-night risky shop (+35): electronics, at 04:53. That makes 65 points, over the 60 needed to block it. The customer reported it as fraud five days later, so blocking it was right. This looks like a hijacked account.
What the tools return on the full dataset:
try_thresholds(review_at=30, block_at=50)
current : blocked automatically 77.2% of stolen €, 93.6% with review
what-if : blocked 389 payments, 253 of them genuine customers ...
try_check_setting("R4", "multiple", 12)
current (8×) : 3,517 alerts, precision 2.8%, catches 78.7% of stolen €
what-if (12×): 1,626 alerts, precision 4.4%, catches 62.1% of stolen €Set it up
Needs Python 3.12+, git and uv.
1. Get Ledger and build its database (one time, about a minute):
uvx --from git+https://github.com/DiogoS7/Ledger-MCP ledger-mcp setupThis clones Ledger into ~/.ledger-mcp/Ledger and generates data/ledger.db. If you already have a checkout, set LEDGER_HOME to it (and run python -m ledger generate there if there's no database yet).
2. Add it to your MCP client.
Claude Code:
claude mcp add ledger -- uvx --from git+https://github.com/DiogoS7/Ledger-MCP ledger-mcpClaude Desktop (claude_desktop_config.json), or any client that takes the same format:
{
"mcpServers": {
"ledger": {
"command": "uvx",
"args": ["--from", "git+https://github.com/DiogoS7/Ledger-MCP", "ledger-mcp"],
"env": { "LEDGER_HOME": "/path/to/Ledger" }
}
}
}env is optional. Without it the server uses ~/.ledger-mcp/Ledger. Set LEDGER_DB to use a database somewhere else.
How it works
MCP client (Claude)
│ stdio
▼
ledger_mcp/server.py 12 tools · 2 resources · 2 prompts (mcp 2.x MCPServer)
│ imports
▼
Ledger checkout ledger.rules → the six checks, scoring, thresholds
($LEDGER_HOME) ledger.db → runs sql/analysis/*.sql and sql/rules/*.sql
│ read-only
▼
data/ledger.db customers · cards · merchants · transactions · chargebacksThe first call that needs the checks runs all six over the 430k payments (about 7 seconds) and keeps the result in memory until the database file changes. After that, explain_payment, find_payments and try_thresholds answer instantly. try_check_setting re-runs a single check, which takes about 3 seconds.
Develop
git clone https://github.com/DiogoS7/Ledger-MCP && cd Ledger-MCP
git clone https://github.com/DiogoS7/Ledger ../Ledger
LEDGER_HOME=../Ledger uv run pytest -qThe tests build a small Ledger database (250 customers) and talk to the server through an in-memory MCP client. They cover every tool, both resources, a prompt, and the read-only guarantees. To try it by hand, use the MCP Inspector: npx @modelcontextprotocol/inspector uv run ledger-mcp.
The data is synthetic. No real people or banks are involved.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
A paid remote MCP for AI SDK data query MCP, built to return verdicts, receipts, usage logs, and aud
Read-only finance and operations controls for AI agents with evidence and safe next actions.
Read-only AI coding tools for change verification, release readiness, capacity, and guidance.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables real-time fraud detection and transaction analysis by integrating with Claude through MCP, providing tools to analyze transactions, flag suspicious activity, and manage fraud rules.9-
- FlicenseNot gradedqualityDmaintenanceEnables read-only access to company data across PostgreSQL, MongoDB Atlas, and flat files through MCP tools, allowing AI assistants to query and retrieve information via natural language.-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to query internal business data for insights into customers, revenue, subscriptions, sales, and churn through controlled, read-only MCP tools.-
- AlicenseNot gradedqualityCmaintenanceEnables agents to interrogate payment routing decisions through six tools: route transactions, explain decisions, simulate scenarios, inspect segment evidence, normalize decline codes, and review backtest summaries. It provides read-only access to the routing engine, allowing natural-language queries without modifying any decisions.MIT