ntriq-agentshop
MCP server for document intelligence via x402 micropayments. 6 tools: document analysis, invoice extraction, screenshot data, alt text, PII detection, sentiment analysis. Pay-per-use with USDC on Base — no API keys needed.
README
ntriq-agentshop — Document Intelligence via x402 Micropayments
MCP server exposing AI-powered document intelligence endpoints with pay-per-use pricing via x402 micropayments (USDC on Base). No API keys, no subscriptions — AI agents pay only for what they use.
MCP Tools
| Tool | Description | Price |
|---|---|---|
document_intelligence |
Extract text, summarize, classify, or extract tables from document images | $0.05 |
invoice_extract |
Extract structured fields from invoices and receipts | $0.03 |
screenshot_data |
Extract structured data from UI screenshots and dashboards | $0.02 |
alt_text |
Generate accessible alt text for images | $0.01 |
pii_detect |
Detect and redact PII in text | $0.02 |
sentiment_analysis |
Analyze text sentiment with score and key phrases | $0.01 |
Install
Claude Code / Cursor / Windsurf
Add to your MCP config:
{
"mcpServers": {
"ntriq-agentshop": {
"command": "npx",
"args": ["-y", "ntriq-agentshop"],
"env": {
"X402_PAYMENT_HEADER": "<your-x402-payment-header>"
}
}
}
}
Payment Setup
This server uses x402 micropayments on Base mainnet (USDC).
- Get a Base wallet with USDC
- Generate an EIP-3009 payment authorization for each request
- Pass it as
X402_PAYMENT_HEADERenv var
Payment recipient: 0x124AaFfF8Ef45F2cA953807aF09Aacec2D9F8307
Architecture
AI Agent (Claude / Cursor / etc.)
↓ MCP stdio
ntriq-agentshop MCP Server
↓ HTTPS + x402 payment header
x402 Data Intelligence Server (https://x402.ntriq.co.kr)
↓
Local AI (qwen2.5-vl vision model)
Partners & Ecosystem
AsterPay
Trust, discovery, and fiat settlement layer for AI agent commerce.
KYA trust scoring (0-100), source-bounded fact-checking (AI Verify), USDC/EURe → EUR SEPA settlement. ERC-8004 native (Agent #16850).
- Website: asterpay.io
- API docs: asterpay.io/docs
- MCP:
npx -y @asterpay/mcp-server - Demo: asterpay.io/verify
ntriq-agentshop is registered on the AsterPay ecosystem as Agent #16850. Agents interacting with this server can verify trust scores via:
POST https://x402.asterpay.io/v1/agent/trust-score
Body: { "agent_id": "erc8004:<address>" }
Running Locally
git clone https://github.com/ntriq-gh/ntriq-agentshop
cd ntriq-agentshop
npm install
X402_BASE_URL=https://x402.ntriq.co.kr node --import tsx mcp-server.ts
License
MIT
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.