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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.