A professional-grade Mercury banking integration for AI agents that automates transaction tracking, cash flow analysis, and financial categorization.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mercury-banking
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install mercury-banking using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Mercury Banking?
The Mercury Banking skill provides a robust bridge between the Mercury API and your AI-driven workflows. It allows developers to programmatically access account balances, detailed transaction histories, and real-time financial metrics. By leveraging this integration within the Openclaw Skills framework, businesses can move beyond manual banking exports to a state of automated, real-time capital oversight.
This skill is designed for technical users who need to build financial dashboards, automate expense reporting, or monitor burn rates. It combines raw API access with advanced logic for cash flow calculation and optional AI processing for smarter data interpretation. Using Openclaw Skills like this ensures your financial data is accessible and actionable for your autonomous agents.
Mercury Banking Use Cases
- Building automated weekly financial summaries and cash flow reports for stakeholders.
- Using AI to categorize thousands of transactions into buckets like SaaS, Payroll, and Marketing.
- Monitoring business runway and burn rates through automated CLI checks.
- Exporting specific transaction sets filtered by date or counterparty for accounting preparation.
- Enabling Openclaw Skills to provide real-time balance alerts and financial insights.
How Mercury Banking Works
- The skill authenticates with the Mercury API v1 using a secure Bearer token provided in your environment variables.
- When a command is issued, the script queries specific endpoints for accounts, transactions, or balance data.
- The system automatically handles pagination to ensure no data is missed during large transaction fetches.
- If an OpenRouter key is provided, transaction descriptions are processed through an LLM for intelligent categorization.
- The results are formatted into clean, readable outputs or summaries suitable for further automation within Openclaw Skills.
Mercury Banking Setup
To get started, ensure you have Python 3.10+ installed and a Mercury API token from your account settings.
# Set required environment variables
export MERCURY_API_KEY='your_mercury_token_here'
# Optional: Set OpenRouter key for AI categorization features
export OPENROUTER_API_KEY='your_openrouter_token_here'
# Verify the installation by listing your accounts
python3 scripts/mercury_api.py accounts
Mercury Banking Data Schema & Taxonomy
The skill organizes financial data into structured outputs based on the Mercury schema, optimized for both human reading and machine processing.
| Component | Information Tracked |
|---|---|
| Accounts | ID, Type, Current Balance, Status, Account Name |
| Transactions | Timestamp, Counterparty, Amount, Status, Description, AI-Category |
| Cash Flow Metrics | Total Inflows, Total Outflows, Net Position, Daily Average, Burn Rate |
| Summaries | Top Expenses, Revenue Sources, Period-over-Period Trends |
Mercury Banking Advanced Features
- Intelligent transaction categorization using LLMs to simplify bookkeeping workflows.
- Detailed cash flow analysis calculating burn rates and daily averages automatically.
- Advanced filtering by transaction status (pending, sent, failed) and date ranges.
- Seamless integration into larger multi-agent systems via the Openclaw Skills ecosystem.
- Automatic pagination management for processing high-volume transaction accounts.
SKILL.md
Loading
Related Openclaw Skills
Make (Integromat) Automation
A high-performance Python tool for managing Make automation scenarios, executions, connections, and data stores through a zero-dependency API interface.
Mac Mini AI Server for OpenClaw
A comprehensive deployment guide for running Openclaw Skills on a dedicated Mac Mini server for 24/7 AI availability.
Loom
A Python-powered interface to manage Loom video recordings, transcripts, and workspace folders via the official Developer API.
LLM Evaluator
An automated LLM-as-a-Judge evaluation system for scoring AI response quality, accuracy, and hallucination using Langfuse.
Model Audit
A comprehensive auditing tool that compares your current LLM stack against live OpenRouter pricing to find cheaper and more powerful model alternatives.
Model Audit
A diagnostic tool within the Openclaw Skills ecosystem designed to audit LLM stacks against live OpenRouter pricing and performance benchmarks.
Featured*
