Zilliqa MCP Server
Provides access to Zilliqa blockchain documentation and API examples through search capabilities and examples in multiple programming languages.
README
Zilliqa MCP Server
A comprehensive Model Context Protocol (MCP) server that provides access to Zilliqa blockchain documentation, API examples, address conversion tools, faucet integration, live network statistics, and automatic content fetching from source URLs.
Installation
Using Local Development Version
Clone this repository and build the local instance:
git clone https://github.com/Zilliqa/zilliqa-experimental.git
cd zilliqa-experimental/lama/zilliqa-mcp
npm install
npm run build
Features
Documentation & API Access
- search_zilliqa_docs - Search through Zilliqa documentation for specific topics
- get_zilliqa_api_example - Get specific API examples by name and programming language
- list_zilliqa_apis - List all available API methods in the documentation
- get_zilliqa_network_info - Get network information (RPC URLs, chain IDs, explorers, faucets)
Address Conversion Tools
- convert_zilliqa_address - Convert between bech32 (zil1...) and hex address formats
- validate_zilliqa_address - Validate Zilliqa address format without conversion
- batch_convert_zilliqa_addresses - Convert multiple addresses at once (up to 100 addresses)
Faucet Integration
- request_zilliqa_faucet - Request test ZIL tokens from devnet/testnet faucets (100 ZIL per request)
Network Statistics
- get_network_stats - Get live network statistics for mainnet, testnet, and devnet
- Latest block information (number, timestamp, gas usage)
- Network status and configuration
- Real-time blockchain metrics
Staking Portal Information
- get_staking_portal_info - Get comprehensive information about Zilliqa 2.0 staking portal (stake.zilliqa.com)
- Overview of staking portal features and functionality
- Liquid staking vs non-liquid staking options
- Validator selection guidance and considerations
- Step-by-step staking instructions
- Staking requirements and minimum amounts
- Rewards information and claiming process
Smart Content Fetching
- Universal Source URL Fetching - Automatically fetches and includes live content from any source URLs mentioned in documentation
- Enhanced Content Extraction - Intelligently extracts main content from various website structures
- Real-time Documentation - Always provides up-to-date information by fetching from original sources
Claude Desktop Integration
Add this to your Claude Desktop MCP configuration:
{
"mcpServers": {
"zilliqa": {
"command": "node",
"args": ["/path/to/zilliqa-experimental/lama/zilliqa-mcp/build/index.js"]
}
}
}
Replace /path/to/zilliqa-experimental with the actual path where you cloned the repository.
Configuration File Location
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Usage Examples
After installation and configuration, you can use these tools in Claude:
Documentation & API Examples
- "Search Zilliqa docs for GetBalance"
- "Get API example for GetTransaction in Python"
- "List all available Zilliqa APIs"
- "Get devnet network information"
Address Conversion
- "Convert this address to hex: zil1abc123..."
- "Validate this Zilliqa address: 0x123abc..."
- "Convert these addresses in batch: [zil1abc..., 0x123...]"
Faucet Requests
- "Request devnet tokens for zil1abc123..."
- "Get testnet ZIL for my address"
Network Statistics
- "Get mainnet network statistics"
- "Show testnet network stats"
- "Get devnet blockchain metrics"
Staking Portal Information
- "Get staking portal overview"
- "Tell me about liquid staking options"
- "How do I stake on Zilliqa 2.0?"
- "What are the staking requirements?"
- "Explain validator selection process"
- "How do I claim staking rewards?"
Smart Features
- All responses automatically include live content from source URLs
- Documentation is always up-to-date with latest information
- Addresses are automatically formatted in code blocks for easy copying
Technical Details
Supported Networks
- Devnet - Development network with latest features (Chain ID: 33103)
- Testnet - Stable testing environment (Chain ID: 33101)
- Mainnet - Production network (Chain ID: 32769)
Address Formats
- Bech32 - Human-readable format (zil1...) - recommended for user interfaces
- Hex - Machine-readable format (40 characters, with/without 0x prefix)
- Validation - Comprehensive format checking with detailed error messages
API Documentation
The server includes comprehensive Zilliqa API documentation with examples in:
- Java
- Python
- Go
- Node.js
- cURL
Access patterns include blockchain APIs, transaction handling, and smart contract interactions.
Smart Content Features
- Universal URL Detection - Automatically detects any HTTP/HTTPS URL in documentation
- Content Extraction - Intelligently extracts main content from various website structures
- Fallback Mechanisms - Graceful handling when content cannot be fetched
- Live Documentation - Always provides current information from original sources
Network Statistics Sample Output
**Mainnet Network Statistics**
**Latest Block:**
- Block Number: 5474727
- Timestamp: 2025-07-08T15:49:58.395Z
- Gas Limit: 200000
- Gas Used: 0
- Transaction Count: 64
**Network Info:**
- Network ID: 1
- Chain ID: 32769
- Status: 🟢 Online
**Configuration:**
- RPC URL: https://api.zilliqa.com
- Explorer: https://explorer.zilliqa.com
Development
Local Development
git clone https://github.com/Zilliqa/zilliqa-experimental.git
cd zilliqa-experimental/lama/zilliqa-mcp
npm install
npm run build
npm run dev
HTTP Server Mode
For development and testing, you can run the server in HTTP mode:
MCP_TRANSPORT=http npm start
This runs the server on port 3000 with CORS enabled for testing.
Testing
npm test
Project Structure
src/
├── index.ts # Main MCP server implementation
├── LLMtext/ # Documentation files
│ ├── ZilliqaBlockcahin.txt
│ ├── ZilliqaDevDocs.txt
│ └── ...
build/ # Compiled JavaScript files
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。