技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 161 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：aiwithabidi/mercury-banking
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill is internally consistent with a Mercury banking integration: it only requires a Mercury API key, calls the Mercury API, and optionally uses OpenRouter for LLM-based categorization — nothing in the files appears to be doing unrelated or hidden actions.
目的
Name/description, declared primary credential (MERCURY_API_KEY), SKILL.md usage examples, and the included script all align: the code calls https://api.mercury.com/api/v1 for accounts/transactions/cashflow and implements the described commands.
说明范围
Runtime instructions and the script stay within banking and optional AI categorization. However, the tool prints account and routing numbers and will send transaction lists to OpenRouter (an external LLM endpoint) when AI features are used — this exposes sensitive financial data to a third party if you enable categorization/summary without reviewing data policies.
安装机制
Instruction-only with a single Python script and no install spec; nothing is downloaded or extracted during install.
证书
Only MERCURY_API_KEY is required (declared as primary). That is expected for this integration but is a high‑privilege secret because it grants access to account and transaction data. OPENROUTER_API_KEY is optional for LLM features and is only needed when calling AI endpoints.
持久
The skill does not request always:true, does not modify other skills or system settings, and is user-invocable. It runs on demand and does not demand permanent presence.
综合结论
This skill appears to do what it says, but take these precautions before installing: 1) Only provide a Mercury API key with the minimal scope required (use sandbox/test tokens when possible) and be prepared to rotate the key if needed. 2) Be aware that enabling AI features will send transaction data to OpenRouter (an external LLM) — avoid sending sensitive PII or confidential transactions unless you are comfortable with that third party's poli…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Mercury Banking」。简介：Mercury banking API integration — accounts, balances, transactions, financial s…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/aiwithabidi/mercury-banking/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: mercury-banking
description: Mercury banking API integration — accounts, balances, transactions, financial summaries, AI transaction categorization, and cash flow analysis. The only Mercury banking skill on ClawHub. Use for business banking, financial tracking, and expense management.
homepage: https://www.agxntsix.ai
license: MIT
compatibility: Python 3.10+, Mercury banking account
metadata: {"openclaw": {"emoji": "ud83cudfe6", "requires": {"env": ["MERCURY_API_KEY"]}, "primaryEnv": "MERCURY_API_KEY", "homepage": "https://www.agxntsix.ai"}}
---
# 🏦 Mercury Banking
Mercury banking API integration for OpenClaw agents. Manage accounts, transactions, cash flow, and get AI-powered financial insights.
## Requirements
| Variable | Required | Description |
|----------|----------|-------------|
| `MERCURY_API_KEY` | ✅ | Mercury API token ([get one](https://app.mercury.com/settings/tokens)) |
| `OPENROUTER_API_KEY` | Optional | For AI categorization and summaries |
## Quick Start
```bash
# List all accounts and balances
python3 {baseDir}/scripts/mercury_api.py accounts
# Recent transactions
python3 {baseDir}/scripts/mercury_api.py transactions <account_id>
# Transactions with date filter
python3 {baseDir}/scripts/mercury_api.py transactions <account_id> --start 2026-01-01 --end 2026-01-31
# Search transactions
python3 {baseDir}/scripts/mercury_api.py transactions <account_id> --search "Stripe"
# Cash flow analysis
python3 {baseDir}/scripts/mercury_api.py cashflow <account_id> --days 30
# AI categorize transactions
python3 {baseDir}/scripts/mercury_api.py categorize <account_id> --days 30
# Financial summary
python3 {baseDir}/scripts/mercury_api.py summary <account_id> --period weekly
```
## Commands
### `accounts`
Lists all Mercury accounts with current balances, account type, and status.
### `transactions <account_id>`
Fetch transactions with optional filters:
- `--start YYYY-MM-DD` / `--end YYYY-MM-DD` — date range
- `--search "term"` — filter by counterparty or description
- `--limit N` — max results (default 50)
- `--status pending|sent|cancelled|failed` — filter by status
### `cashflow <account_id>`
Analyze cash flow over a period:
- `--days N` — lookback period (default 30)
- Shows total inflows, outflows, net, daily average, burn rate
### `categorize <account_id>`
AI-powered transaction categorization (requires `OPENROUTER_API_KEY`):
- `--days N` — lookback period (default 30)
- Groups transactions into categories (payroll, SaaS, revenue, etc.)
- Outputs category totals and percentages
### `summary <account_id>`
Generate financial summary:
- `--period weekly|monthly` — summary period
- Includes top expenses, revenue sources, cash position, trends
## Mercury API Notes
- **Base URL:** `https://api.mercury.com/api/v1`
- **Auth:** Bearer token in Authorization header
- **Rate limits:** Be mindful of API limits; the script handles pagination automatically
- **Sandbox:** Mercury provides a sandbox environment for testing
## Credits
Built by [M. Abidi](https://www.linkedin.com/in/mohammad-ali-abidi) | [agxntsix.ai](https://www.agxntsix.ai)
[YouTube](https://youtube.com/@aiwithabidi) | [GitHub](https://github.com/aiwithabidi)
Part of the **AgxntSix Skill Suite** for OpenClaw agents.
📅 **Need help setting up OpenClaw for your business?** [Book a free consultation](https://cal.com/agxntsix/abidi-openclaw)