legal-doc-intelligence
MCP server that analyzes legal documents, extracts key clauses, identifies risks, and summarizes contracts. 8 tools for AI agents needing legal document intelligence.
README
Legal Doc Intelligence — Pay-Per-Call MCP Server
An MCP server that exposes 8 AI-powered legal document analysis tools, each billed per call in USDC on Base via the x402 payment protocol. No accounts, no subscriptions — agents pay only for what they use.
Live endpoint: https://income-machine-production.up.railway.app/mcp
Health check: https://income-machine-production.up.railway.app/health
Transport: HTTP (Streamable HTTP / MCP 2025-11-25)
Tools & Pricing
| Tool | Description | Price |
|---|---|---|
extract_clauses |
Extract and categorize all clauses from a contract | $0.02 USDC |
identify_risks |
Identify legal risks, red flags, and unfavorable terms | $0.05 USDC |
compare_contracts |
Compare two contracts and highlight differences | $0.05 USDC |
extract_parties |
Extract all parties, roles, and contact info | $0.01 USDC |
summarize_contract |
Generate an executive summary for non-lawyers | $0.02 USDC |
check_compliance |
Check compliance with GDPR, CCPA, SOX, and others | $0.05 USDC |
extract_obligations |
Extract all obligations, deadlines, and deliverables | $0.02 USDC |
calculate_penalty_exposure |
Calculate maximum financial penalty exposure | $0.05 USDC |
Prices auto-adjust downward if call volume drops below the 7-day average.
Payment Protocol (x402)
Payments use the x402 HTTP payment standard:
- Call any tool without a
payment_header→ server returns a402 Payment Requiredresponse withPaymentRequirements - Client constructs a USDC payment on Base to
0xF4641f6AF6cc32c588Fa948ff64dBC0974F7D290 - Client encodes the signed payment as a base64
payment_headerand retries the call - Server verifies and settles on-chain, then returns the result
Network: Base (Coinbase L2)
Token: USDC (0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)
Receiver: 0xF4641f6AF6cc32c588Fa948ff64dBC0974F7D290
Quick Start — Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"legal-doc-intelligence": {
"url": "https://income-machine-production.up.railway.app/mcp",
"transport": "http"
}
}
}
You will need a Base wallet with USDC to pay for tool calls. Compatible wallets: Coinbase Wallet, MetaMask with Base network.
Quick Start — Programmatic (Node.js)
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";
const client = new Client({ name: "my-agent", version: "1.0.0" });
await client.connect(
new StreamableHTTPClientTransport(
new URL("https://income-machine-production.up.railway.app/mcp")
)
);
// First call returns payment requirements
const result = await client.callTool("identify_risks", {
contract_text: "...",
jurisdiction: "EU",
});
// If result contains x402: true, construct payment and retry with payment_header
Self-Hosting
Requirements
- Node.js 20+
- A Base wallet with ETH (gas) and USDC
- Railway / Fly.io / any Node.js host
Environment Variables
ANTHROPIC_API_KEY= # Claude API key for AI processing
CDP_PRIVATE_KEY= # Private key of the Base wallet (0x...)
WALLET_ADDRESS= # Public address of the same wallet
KRAKEN_API_KEY= # Optional: auto-convert USDC → EUR via Kraken
KRAKEN_API_SECRET= # Optional
KRAKEN_DEPOSIT_ADDRESS= # Optional: your Kraken USDC deposit address on Base
TELEGRAM_BOT_TOKEN= # Optional: alerts
TELEGRAM_CHAT_ID= # Optional
DASHBOARD_PASSWORD= # Password for the private /dashboard endpoint
PORT=3000
BASE_URL= # Your public URL, e.g. https://your-app.railway.app
Run
npm install
npm run build
npm start
Architecture
- MCP server — Express +
@modelcontextprotocol/sdk, HTTP transport - Payment layer —
x402npm package for verify + settle on Base - Auto-conversion — Kraken API polls USDC balance and converts to EUR when threshold is met
- Autopilot — cron job scans HN for new MCP marketplaces weekly and adjusts prices nightly
- Alerts — Telegram bot notifies on payments, errors, and conversions
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。