Coddie MCP Server
Secure read-only access to Coddie project planning data, enabling AI assistants to manage and query projects, phases, and steps.
README
Coddie MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with secure, read-only access to your Coddie project planning data. This allows AI assistants like Claude, Cursor, and Windsurf to help you work with your existing projects, development phases, implementation steps, and project rules.
What is Coddie?
Coddie is a SaaS project planning application that helps developers transform ideas into structured, production-ready development plans. It uses an interactive 4-step planning process and generates comprehensive PRD documents, development phases, and actionable implementation steps focused on Next.js + TypeScript + Supabase applications.
Prerequisites
- Node.js (version 18 or higher)
- A Coddie account with existing projects
- API key from your Coddie account settings
Setup
1. Get Your Coddie API Key
- Log in to your Coddie account
- Navigate to Settings → API Keys
- Generate a new API key for MCP access
- Copy the generated API key (you'll need it for configuration)
2. Configure Your AI Assistant
Claude Desktop
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"coddie": {
"command": "npx",
"args": [
"-y",
"@coddieapp/mcp-server@latest",
"--api-key",
"your_coddie_api_key_here"
]
}
}
}
Other AI Assistants
For Cursor or Windsurf, follow their respective MCP configuration documentation using the same command structure above.
3. Restart Your AI Assistant
After updating the configuration file, restart your AI assistant to load the Coddie MCP server.
Security Considerations
⚠️ Important Security Notes:
- Read-only access: This MCP server provides read-only access to your Coddie data
- API key security: Keep your API key secure and don't share it publicly
- Project scoping: The server only accesses projects belonging to your authenticated account
- Review tool calls: Always review what the AI assistant is requesting before allowing tool execution
Available Tools
The Coddie MCP server provides these tools to AI assistants:
Project Management
list_projects- List all your Coddie projectsget_project_info- Get detailed project information (name, description, tech stack, status)get_context- Get development progress and context summary for a project
Features & Planning
list_features- List all features for a specific project
Development Phases
list_phases- List all development phases for a projectget_phase- Get detailed phase information (title, description, status)list_steps- List all implementation steps for a specific phaseget_step- Get detailed step information (content, code examples, completion status)
Project Rules
list_rules- List all rules for a specific projectget_rule- Get detailed rule information (file patterns, content, descriptions)
Example Usage
Once configured, you can ask your AI assistant questions like:
- "What projects do I have in Coddie?"
- "Show me the current phase for my e-commerce project"
- "What implementation steps are left in the authentication phase?"
- "What are the coding rules for my SaaS project?"
Troubleshooting
"API key is required" error
- Ensure you've added the
--api-keyargument to your configuration - Verify your API key is correct and not expired in Coddie settings
"HTTP error! status: 401"
- Your API key may be invalid or revoked
- Generate a new API key in your Coddie account settings
Connection issues
- Ensure you have an active internet connection
- Check that you can access coddie.dev in your browser
- Restart your AI assistant after configuration changes
Contributing
This MCP server is open source. Feel free to submit issues and pull requests on GitHub.
Support
- Documentation: Coddie Help Center
- Issues: GitHub Issues
- Contact: support@coddie.dev
Note: This MCP server requires an active Coddie account and existing projects to be useful. If you're new to Coddie, sign up and create your first project!
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。