nanoparse-mcp
MCP server that enables AI agents to fetch web content as clean, structured Markdown via NanoParse's hosted API, using x402 micropayments in USDC on Base.
README
NanoParse MCP
MCP client for NanoParse — pay-per-parse web content extraction for AI agents. No accounts, no API keys. Just paste a URL and get clean, structured Markdown back.
What this is
A thin MCP (Model Context Protocol) client that lets AI agents call NanoParse's hosted API. The client handles:
- MCP tool registration (
nanoparse_fetch) - HTTP calls to
nanoparse.app/fetch - x402 micropayment signing (USDC on Base)
The browser rendering, content scoring, and Markdown conversion stay on NanoParse's infrastructure — this repo is the client layer only.
Install
npx nanoparse-mcp
Or install globally:
npm install -g nanoparse-mcp
Prerequisites
- Node.js 18+
- A Base wallet with USDC (after your first 50 free parses)
- Set
NANOPARSE_WALLET_KEYin your environment
Getting a wallet
If you don't already have a Base-compatible wallet for your agent, don't generate one by hand — use NanoParse/agent-wallet-prompt, a copy-paste prompt that walks your coding assistant through generating one safely with an audited library. Come back here once it's funded.
Setup
-
Copy the environment template:
cp .env.example .env -
Edit
.envand add your Base wallet private key:NANOPARSE_WALLET_KEY=0x_your_private_key_here -
Add to your MCP client config:
{ "mcpServers": { "nanoparse": { "command": "npx", "args": ["nanoparse-mcp"] } } }
Your agent will auto-discover the nanoparse_fetch tool.
Usage
Your agent calls nanoparse_fetch with a URL:
nanoparse_fetch("https://example.com/article")
Optional debug mode:
nanoparse_fetch("https://example.com/article", debug=true)
See examples/basic-usage.md for a full copy-paste runnable example.
Pricing
First 50 calls per IP are free. After that, $0.0175 per parse via x402 micropayment in USDC on Base. See nanoparse.app for current pricing and API docs.
Security
- Your private key is read from
NANOPARSE_WALLET_KEYat runtime and is never logged, printed, or transmitted except for signing x402 payment requests. - The
.envfile is excluded from git via.gitignore. - Payment signing uses viem, an established, audited Ethereum library.
- This client never constructs raw blockchain transactions — payment settlement is handled by the x402 facilitator.
Versioning
This project follows Semantic Versioning. See CHANGELOG.md for release history.
License
MIT — see LICENSE.
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。