req-refine MCP server
ReqRefine is an MCP server that enhances requirement gathering through strategic questioning. It guides users to reveal comprehensive needs, uncovers implicit requirements, and transforms dialogue into structured specifications.
What is ReqRefine?
ReqRefine is an MCP server designed to enhance requirement gathering through strategic questioning. It helps users uncover comprehensive needs and implicit requirements, transforming dialogue into structured specifications.
How to use ReqRefine?
To use ReqRefine, set up the server and utilize its note storage system to add and summarize notes. You can interact with the server using the provided tools and prompts.
Key features of ReqRefine?
- Strategic questioning to reveal user needs
- Note storage system with custom URI scheme
- Summarization of notes with adjustable detail levels
- Collaborative discovery process for requirements collection
Use cases of ReqRefine?
- Facilitating requirement gathering in software development projects.
- Enhancing communication between stakeholders during project planning.
- Structuring user feedback into actionable specifications.
FAQ from ReqRefine?
- Can ReqRefine handle complex requirements?
Yes! ReqRefine is designed to manage complex requirements through its strategic questioning approach.
- Is there a user guide available?
Yes! Detailed configuration and usage instructions are provided in the project documentation.
- What programming language is ReqRefine built with?
ReqRefine is built using Python.
req-refine MCP server
ReqRefine is an MCP conversational service that enhances requirement gathing through strategic questioning.It guides users to reveal comprehensive needs, unconvers implict requirements, and transforms dialogue into structured specifications. ReqRefine turns requirements collection from a one-side interview into a collaborative dicovery process.
Components
Resources
The server implements a simple note storage system with:
- Custom note:// URI scheme for accessing individual notes
- Each note resource has a name, description and text/plain mimetype
Prompts
The server provides a single prompt:
- summarize-notes: Creates summaries of all stored notes
- Optional "style" argument to control detail level (brief/detailed)
- Generates prompt combining all current notes with style preference
Tools
The server implements one tool:
- add-note: Adds a new note to the server
- Takes "name" and "content" as required string arguments
- Updates server state and notifies clients of resource changes
Configuration
[TODO: Add configuration details specific to your implementation]
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration
``` "mcpServers": { "req-refine": { "command": "uv", "args": [ "--directory", "D:\code\mcp-server-req-refine", "run", "req-refine" ] } } ```Published Servers Configuration
``` "mcpServers": { "req-refine": { "command": "uvx", "args": [ "req-refine" ] } } ```Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory D:\code\req-refine run req-refine
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
