interzoid-mcp-server
MCP server exposing 29 AI-powered Interzoid data quality APIs — company/name/address matching and deduplication, business intelligence, email trust scoring, data standardization, verification, translation, and more. Supports API key authentication and x402 crypto micropayments.
README
Interzoid MCP Server
An MCP (Model Context Protocol) server that exposes Interzoid's AI-powered data quality, matching, enrichment, and standardization APIs to AI agents and LLM applications.
What This Does
This MCP server makes 29 Interzoid APIs discoverable and callable by any MCP-compatible client including Claude Desktop, Claude Code, Cursor, Windsurf, and other AI tools. AI agents can discover the available data quality tools and invoke them as needed during conversations and workflows.
Available APIs (29 Tools)
| Category | Tools | Price (USDC) |
|---|---|---|
| Data Matching — Similarity key generation & scoring | Company match, org match score, name match/score, address match, global address, product match | $0.0125/call |
| Data Enrichment — AI-powered intelligence (Premium) | Business info, parent company, executives, news, email trust, stock, verification, IP/phone profiles | $0.3125/call |
| Data Standardization — Canonical form normalization | Org, country, country info, city, state abbreviation | $0.0125/call |
| Data Enhancement — Classification & analysis | Entity type, gender, name origin, language ID, translation (to English & any), address parsing | $0.0125/call |
| Utility — Weather, currency, ZIP lookup | Global weather, exchange rates, ZIP code info | $0.0125/call |
Getting Started
Option 1: Use the Hosted Remote Server (no installation required)
Connect any MCP client that supports remote HTTP servers to:
https://mcp.interzoid.com/mcp
Pass your API key via the Authorization header:
Authorization: Bearer your-api-key-here
Get a free API key at interzoid.com to get started.
Option 2: Download a Prebuilt Binary (no Go required)
Download the binary for your platform from the GitHub Releases page:
- Windows:
interzoid-mcp-server-windows-amd64.exe - macOS (Apple Silicon):
interzoid-mcp-server-macos-arm64 - Linux:
interzoid-mcp-server-linux-amd64
Then configure your MCP client to run it (see Client Configuration below).
Option 3: Build from Source
Requires Go 1.21+:
git clone https://github.com/interzoid/interzoid-mcp-server.git
cd interzoid-mcp-server
go mod tidy
go build -o interzoid-mcp-server .
Authentication
There are three ways to authenticate, depending on how you're using the server:
1. API Key via Environment Variable (local installations)
Set INTERZOID_API_KEY in your MCP client config. This is the standard method when running the binary locally.
export INTERZOID_API_KEY="your-api-key-here"
./interzoid-mcp-server
2. API Key via Authorization Header (remote/hosted server)
When connecting to the hosted server at https://mcp.interzoid.com/mcp or any remote deployment, pass your API key in the Authorization header:
Authorization: Bearer your-api-key-here
The MCP server forwards this to the Interzoid API via the x-api-key header.
3. x402 Crypto Micropayments (no API key needed)
When no API key is provided by either method above, requests trigger the x402 payment protocol. The Interzoid API returns a 402 Payment Required response with payment requirements, and the calling agent/client handles payment negotiation using USDC on Base. No signup or API key is needed — just a compatible wallet.
Where to Get an API Key
Sign up for a free API key at interzoid.com/signup. Keys work with both the local binary (via environment variable) and the remote server (via Authorization header).
Client Configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"interzoid": {
"command": "/path/to/interzoid-mcp-server",
"env": {
"INTERZOID_API_KEY": "your-api-key-here"
}
}
}
}
Claude Code
claude mcp add interzoid -- /path/to/interzoid-mcp-server
Or add to .claude/settings.json:
{
"mcpServers": {
"interzoid": {
"command": "/path/to/interzoid-mcp-server",
"env": {
"INTERZOID_API_KEY": "your-api-key-here"
}
}
}
}
Cursor / Windsurf / Other MCP Clients (remote)
Point the client to the hosted server:
https://mcp.interzoid.com/mcp
Set the Authorization header to Bearer your-api-key-here.
Example Interactions
Once configured, AI agents can use the tools naturally:
User: "Check if 'IBM' and 'International Business Machines' are the same company" Agent uses:
interzoid_org_match_scorewith org1="IBM", org2="International Business Machines" Result: Score: 98
User: "What can you tell me about Anthropic's business?" Agent uses:
interzoid_business_infowith lookup="Anthropic" Result: Headquarters, revenue, employees, industry, description
User: "Translate 'Bonjour le monde' to English" Agent uses:
interzoid_translate_to_englishwith text="Bonjour le monde" Result: Translation: "Hello world"
Self-Hosting the Remote Server
To host your own remote instance:
./interzoid-mcp-server -transport http -port 8080
The MCP endpoint will be available at http://localhost:8080/mcp. Place behind Nginx or a load balancer with HTTPS for production use. Ensure proxy_buffering off is set in your Nginx config to support SSE streaming.
x402 Payment Integration
All Interzoid APIs support the x402 protocol for native crypto micropayments. When accessed without an API key:
- Standard APIs: 12,500 atomic USDC ($0.0125) per call
- Premium APIs: 312,500 atomic USDC ($0.3125) per call
- Network: Base (EIP-155:8453)
- Asset: USDC (0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)
The .well-known/x402.json manifest at https://api.interzoid.com/.well-known/x402.json provides full machine-readable discovery for x402 clients.
Project Structure
interzoid-mcp-server/
├── main.go # Entry point, transport selection (stdio/HTTP)
├── tools.go # MCP tool registration for all 29 APIs
├── client.go # HTTP client for calling api.interzoid.com
├── go.mod # Go module definition
└── README.md # This file
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。