Birdeye MCP Server

Birdeye MCP Server

Provides blockchain data context from Birdeye APIs for AI models via Model Context Protocol, enabling token, market, wallet, NFT, and DEX pool queries on Solana.

Category
访问服务器

README

Birdeye MCP Server

A Model Context Protocol (MCP) server implementation for the Birdeye APIs. This server acts as a middleware between AI models and the Birdeye blockchain data APIs, providing context about tokens, markets, wallets, NFTs, and more on the Solana blockchain.

What is Model Context Protocol (MCP)?

Model Context Protocol (MCP) is a standardized way for AI models to request and receive contextual information from external data sources. This implementation focuses on providing blockchain and crypto-specific context from Birdeye's APIs.

Features

  • Token information and prices
  • Market data and analytics
  • Wallet portfolio tracking
  • NFT collections and items
  • DEX pools and liquidity
  • MCP-friendly endpoints for AI context generation

Prerequisites

  • Node.js (v14+ recommended)
  • Birdeye API key (get one from Birdeye)

Installation

Standard Installation

  1. Clone this repository

    git clone <repository-url>
    cd birdeye-mcp-server
    
  2. Install dependencies

    npm install
    
  3. Configure environment variables

    cp .env.example .env
    

    Then edit the .env file and add your Birdeye API key.

Docker Installation

  1. Clone this repository

    git clone <repository-url>
    cd birdeye-mcp-server
    
  2. Configure environment variables

    cp .env.example .env
    

    Then edit the .env file and add your Birdeye API key.

  3. Build and start with Docker Compose

    docker-compose up -d
    

Usage

Start the server (Standard)

npm start

The server will run on port 3000 by default (configurable in .env).

Start the server (Docker)

docker-compose up -d

To view logs:

docker-compose logs -f

To stop the server:

docker-compose down

API Endpoints

Standard Birdeye Endpoints

  • GET /token/:network/:address - Get token information
  • GET /price/:network/:address - Get token price
  • GET /price/history/:network/:address - Get token price history
  • GET /market/:network/:address - Get market information
  • GET /tokens/top/:network - Get top tokens
  • GET /token/:network/:address/holders - Get token holders
  • GET /token/:network/:address/transfers - Get token transfers
  • GET /wallet/:network/:address - Get wallet portfolio
  • GET /wallet/:network/:address/tokens - Get wallet tokens
  • GET /nft/collections/:network - Get NFT collections
  • GET /nft/collection/:network/:address - Get NFT collection info
  • GET /nft/item/:network/:address - Get NFT item info
  • GET /dex/pools/:network - Get DEX pools
  • GET /dex/pool/:network/:address - Get DEX pool info

MCP-Specific Endpoints

  • POST /mcp/token - Get comprehensive token context

    {
      "network": "solana",
      "address": "token_address",
      "context": "optional query context"
    }
    
  • POST /mcp/wallet - Get comprehensive wallet context

    {
      "network": "solana",
      "address": "wallet_address",
      "context": "optional query context"
    }
    
  • POST /mcp/market - Get market overview context

    {
      "network": "solana",
      "context": "optional query context"
    }
    

Integrating with AI Models

To use this MCP server with AI models:

  1. Set up the server and ensure it's accessible to your AI system
  2. Configure your AI to make appropriate requests to the MCP endpoints
  3. Parse the contextual information and incorporate it into your model's responses

Example integration:

// From your AI application
async function getBirdeyeContext(tokenAddress) {
  const response = await fetch('http://your-mcp-server/mcp/token', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-API-KEY': 'your_api_key'
    },
    body: JSON.stringify({
      network: 'solana',
      address: tokenAddress,
      context: 'User is asking about token price and market cap'
    })
  });
  
  return await response.json();
}

License

MIT

Integration with Claude or Other MCP-Compatible Agents

To use the Birdeye MCP Server with Claude or any agent that supports the Model Context Protocol (MCP), you can provide the following configuration file (e.g., claude-mcp-server-config.json) to your agent:

{
  "servers": [
    {
      "name": "Birdeye MCP Server",
      "description": "Model Context Protocol server for Birdeye APIs",
      "command": "node",
      "args": ["server.js"],
      "env": {
        "BIRDEYE_API_KEY": "your_birdeye_api_key_here",
        "PORT": "3000"
      },
      "endpoints": [
        {"path": "/mcp/token", "method": "POST", "description": "Get comprehensive token context"},
        {"path": "/mcp/wallet", "method": "POST", "description": "Get comprehensive wallet context"},
        {"path": "/mcp/market", "method": "POST", "description": "Get market overview context"}
      ]
    }
  ]
}

Usage Instructions

  1. Ensure you have set your Birdeye API key in the configuration file above.
  2. Start the MCP server:
    npm install
    npm start
    
  3. Point your Claude agent (or other MCP-compatible agent) to use the above configuration file.
  4. The agent will be able to call the /mcp/token, /mcp/wallet, and /mcp/market endpoints for context-aware queries.

For more details, refer to the claude-mcp-server-config.json file and the API endpoint documentation above.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选