Ogury MCP Server

Ogury MCP Server

An MCP server that gives Claude access to Ogury's campaign reporting API, enabling retrieval of campaign performance metrics and reports through natural language queries.

Category
访问服务器

README

Ogury MCP Server An MCP (Model Context Protocol) server that provides Claude with access to Ogury's campaign reporting API.

Features Authentication: Automatic OAuth2 token management with refresh Campaign Details: Get detailed performance metrics for specific campaigns Campaign Reports: Flexible reporting with multiple filter options Error Handling: Comprehensive error handling and logging Tools Available

  1. get_campaign_details Get detailed performance metrics for a specific campaign.

Parameters:

campaignId (required): The campaign ID to retrieve startDate (required): Start date in YYYY-MM-DD format endDate (required): End date in YYYY-MM-DD format accountId (optional): Account ID filter brandId (optional): Brand ID filter Example usage:

"Please provide details about campaign 12345 for the period from 2024-01-01 to 2024-01-31" 2. get_campaigns_report Get campaign performance report with flexible filtering options.

Parameters:

startDate (required): Start date in YYYY-MM-DD format endDate (required): End date in YYYY-MM-DD format accountId (optional): Account IDs (comma-separated) brandId (optional): Brand ID campaignId (optional): Specific campaign ID identifier1/2/3 (optional): External identifiers

Setup

MCP Client Configuration

To use this MCP server with an MCP client (like Claude Desktop), create a configuration file:

mcp-config.json:

{
  "mcpServers": {
    "ogury": {
      "command": "node",
      "args": ["dist/index.js"],
      "env": {
        "OGURY_CLIENT_ID": "your_ogury_client_id_here",
        "OGURY_CLIENT_SECRET": "your_ogury_client_secret_here"
      }
    }
  }
}

For deployed servers (Railway), use:

{
  "mcpServers": {
    "ogury": {
      "command": "node",
      "args": ["dist/index.js"],
      "env": {
        "OGURY_CLIENT_ID": "your_ogury_client_id_here",
        "OGURY_CLIENT_SECRET": "your_ogury_client_secret_here"
      }
    }
  }
}

Environment Variables

Create a .env file with your Ogury API credentials:

OGURY_CLIENT_ID=your_client_id_here
OGURY_CLIENT_SECRET=your_client_secret_here

Local Development Install dependencies: bash npm install Run in development mode: bash npm run dev Build for production: bash npm run build npm start Deployment on Railway Quick Deploy Create Railway Project Go to Railway Create new project from GitHub repo Connect your repository Set Environment Variables In Railway dashboard: OGURY_CLIENT_ID=your_actual_client_id OGURY_CLIENT_SECRET=your_actual_client_secret Deploy Railway will automatically: Install dependencies (npm install) Build the project (npm run build) Start the server (npm start) Railway Configuration Railway will use these commands automatically:

Build Command: npm run build Start Command: npm start Project Structure ogury-mcp-server/ ├── src/ │ └── index.ts # Main MCP server implementation ├── dist/ # Compiled JavaScript (generated) ├── package.json # Node.js dependencies and scripts ├── tsconfig.json # TypeScript configuration └── README.md # This file How It Works Authentication Flow: Server automatically obtains OAuth2 tokens using client credentials Tokens are cached and refreshed automatically (1-hour expiry) Uses HTTP Basic Auth with base64 encoded CLIENT_ID:CLIENT_SECRET API Integration: Wraps Ogury's /v1/reporting/campaigns endpoint Handles authentication headers and error responses Formats data for Claude consumption MCP Protocol: Exposes tools that Claude can invoke Handles tool discovery and execution Returns structured responses to Claude Testing Once deployed on Railway, you can test by asking Claude:

"Please provide details about campaign 12345 from 2024-01-01 to 2024-01-31" Claude will use the MCP server to:

Authenticate with Ogury API Fetch campaign performance data Format and present the results Error Handling The server includes comprehensive error handling for:

Authentication failures API rate limits Network timeouts Invalid parameters Missing environment variables Security Notes Credentials are stored as environment variables Tokens are cached in memory only (not persisted) All API calls use HTTPS No sensitive data is logged Troubleshooting Common Issues Authentication Failed Verify CLIENT_ID and CLIENT_SECRET are correct Check that credentials have proper API access Campaign Not Found Verify campaign ID exists Check date range is valid for the campaign Ensure account/brand filters are correct Railway Deployment Issues Check environment variables are set Verify build logs in Railway dashboard Ensure Node.js version compatibility (18+) Logs Check Railway logs for detailed error information:

Authentication token requests API call responses MCP protocol messages

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