A TypeScript-based Model Context Protocol (MCP) server that facilitates intelligent feature discussions between developers and AI. This server acts as an AI lead developer, providing guidance on feature implementation, maintaining context of discussions, and helping teams make informed architectural decisions.
This server provides:
- Interactive discussions about feature implementation and architecture
- Persistent memory of feature discussions and decisions
- Intelligent guidance on development approaches and best practices
- Context-aware recommendations based on project history
- Engage in natural discussions about feature requirements
- Get expert guidance on implementation approaches
- Receive architectural recommendations
- Maintain context across multiple discussions
- Persistent storage of feature discussions
- Track feature evolution and decisions
- Reference previous discussions for context
- Link related features and dependencies
- Best practices recommendations
- Implementation strategy suggestions
- Architecture pattern recommendations
- Technology stack considerations
- Maintain project-wide feature context
- Track dependencies between features
- Store architectural decisions
- Remember previous discussion outcomes
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"feature-discussion": {
"command": "/path/to/feature-discussion/build/index.js"
}
}
}
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
We welcome contributions! Please see our Contributing Guidelines for details on how to get started, and our Code of Conduct for community guidelines.
This project is licensed under the MIT License - see the LICENSE file for details.