Canny MCP Server

Canny MCP Server

Enables interaction with Canny.io customer feedback platform through natural language. Supports board management, post creation/updating, search functionality, and comprehensive feedback management operations.

Category
访问服务器

README

Canny MCP Server

A Model Context Protocol (MCP) server that integrates with Canny.io for customer feedback management. Built following CIQ's CODE2 principles to deliver Customer-Centric, Optimistic, Dedicated, Efficient, and Excellent solutions.

Features

Customer-Centric

  • Board Management: List and access all available Canny boards
  • Post Retrieval: Get detailed post information with flexible filtering
  • Search Capability: Find posts across boards using powerful search
  • Content Management: Create and update posts seamlessly

Efficient & Excellent

  • Rate Limiting: Built-in protection against API rate limits
  • Error Handling: Robust error handling with detailed feedback
  • Validation: Input validation using Zod schemas
  • Type Safety: Full TypeScript implementation

Installation

Prerequisites

  • Node.js 18 or higher
  • Canny.io API key

Quick Start

  1. Install dependencies:

    npm install
    
  2. Set up environment variables:

    export CANNY_API_KEY="your_api_key_here"
    export CANNY_BASE_URL="https://canny.io/api/v1"  # Optional
    
  3. Build the server:

    npm run build
    
  4. Run in development mode:

    npm run dev
    

Environment Variables

Required

  • CANNY_API_KEY: Your Canny.io API key

Optional

  • CANNY_BASE_URL: API base URL (default: https://canny.io/api/v1)
  • CANNY_TIMEOUT: Request timeout in ms (default: 30000)
  • CANNY_MAX_RETRIES: Max retry attempts (default: 3)
  • CANNY_RATE_LIMIT_RPM: Requests per minute limit (default: 60)
  • CANNY_RATE_LIMIT_BURST: Burst limit (default: 10)

Available Tools

Board Tools

  • get_boards: List all accessible Canny boards

Post Tools

  • get_posts: Get posts from a specific board with filtering options
  • get_post: Get detailed information about a specific post
  • search_posts: Search for posts across boards
  • create_post: Create a new post in a board
  • update_post: Update an existing post

Usage Examples

Get All Boards

{
  "name": "get_boards",
  "arguments": {}
}

Get Posts from a Board

{
  "name": "get_posts",
  "arguments": {
    "boardId": "board_123",
    "limit": 10,
    "status": "open",
    "sort": "newest"
  }
}

Search Posts

{
  "name": "search_posts",
  "arguments": {
    "query": "feature request",
    "limit": 20,
    "status": "open"
  }
}

Create a Post

{
  "name": "create_post",
  "arguments": {
    "authorId": "user_123",
    "boardId": "board_123",
    "title": "New Feature Request",
    "details": "Detailed description of the feature"
  }
}

Development

Running Tests

npm test

Linting

npm run lint
npm run lint:fix

Building

npm run build

Configuration with Claude

Add to your Claude MCP configuration:

{
  "mcpServers": {
    "canny": {
      "command": "node",
      "args": ["/path/to/canny-mcp-server/dist/server.js"],
      "env": {
        "CANNY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Error Handling

The server implements comprehensive error handling:

  • API rate limiting protection
  • Input validation with detailed error messages
  • Network error recovery with retries
  • Graceful handling of API failures

Contributing

Following CIQ's CODE2 principles:

  1. Customer-Centric: Focus on user value in every contribution
  2. Optimistic: Approach challenges as opportunities
  3. Dedicated: Own your contributions fully
  4. Efficient: Leverage existing solutions and automate where possible
  5. Excellent: Maintain high standards and continuous improvement

License

MIT License

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