The MCP Agile Flow server is a comprehensive system for AI-assisted agile development workflows with a modern API that enables:
- Project Management: Retrieve and configure project settings, paths, type, and metadata
- Thought Management: Record, retrieve, analyze, categorize, and organize development thoughts hierarchically
- Thinking Analysis: Detect thinking directives, assess complexity needs, and provide guidance for deeper analytical thinking
- IDE Support: Initialize directory structures and configuration files for various IDEs (Cursor, Windsurf, Claude-Desktop), including AI templates and rules
- Context Handling: Analyze project documentation and structure to prime context for AI assistants
- Configuration Migration: Transfer MCP configurations and rules between different IDEs
- Natural Language Processing: Interpret and route commands to appropriate tools for execution
MCP Agile Flow
A comprehensive system for managing AI-assisted agile development workflows with a modern, resource-based API using FastMCP.
Status
✅ Migration Complete: The migration from legacy server to FastMCP implementation is fully complete. All legacy code and tests have been removed.
Overview
The MCP Agile Flow project uses a resource-based approach with FastMCP from the official MCP SDK, focusing on:
- RESTful API Design - Clean, intuitive resource URIs for data access
- Resource-First Architecture - Optimized for data retrieval and state representation
- Action-Oriented Tools - Tools used only for operations that modify state
Key Features
- Agile Documentation: Generate and maintain comprehensive AI documentation
- Project Structure: Organize your project with AI-generated files and directories
- IDE Integration: Direct integration with various AI IDEs (Cursor, Windsurf, Cline)
- Workflow Management: Track agile stories and progress
- Intuitive API Structure: Resources organized in a RESTful hierarchy
- Simplified Integration: Direct mapping to resource URIs
- Improved Performance: Optimized for data access patterns
Getting Started
To use MCP Agile Flow:
- Install the package:
- Import in your code:
MCP Client Configuration
Important: Configuration Update Required
If you had previously configured MCP Agile Flow, you need to update your configuration. The fastmcp_server.py
module has been removed as part of code cleanup, and functionality has been consolidated into the main package.
Update your MCP client configuration from:
To:
For Cursor users, also update the mcp.json file (typically at ~/.cursor/mcp.json):
Command Line Usage
You can also run the server directly from the command line:
Available Tools
The MCP Agile Flow provides several tools:
get-project-settings
: Get project settings including paths and environment variablesinitialize-ide
: Initialize project directory structure for specific IDEsinitialize-ide-rules
: Initialize AI rule files for specific IDEsprime-context
: Analyze project documentation and build contextual understandingmigrate-mcp-config
: Migrate MCP configuration between different IDEsthink
: Record a thought for complex reasoning and step-by-step analysisget-thoughts
: Retrieve all thoughts recorded in the current sessionclear-thoughts
: Clear all recorded thoughts from the current sessionget-thought-stats
: Get statistics about the thoughts recorded in the current sessionprocess-natural-language
: Process natural language commands and route to appropriate tools
Natural Language Commands
MCP Agile Flow supports natural language commands, making it easier to interact with the tools without remembering exact command names. Simply use conversational phrases, and the system will automatically detect your intent and map them to the appropriate tools with the correct parameters.
Supported Command Types
Migration Commands
To migrate MCP configuration between different IDEs:
- "migrate mcp config to claude-desktop"
- "migrate config from cursor to claude-desktop"
- "copy mcp settings to windsurf"
- "transfer config to cline"
- "move mcp settings from cursor to roo"
If the source IDE is not specified, it defaults to "cursor".
Note: Valid IDE names are: "cursor", "windsurf-next", "windsurf", "cline", "roo", and "claude-desktop".
Initialization Commands
To initialize a project with rules for a specific IDE:
- "initialize ide for claude"
- "setup rules for windsurf"
- "create ide for cline"
- "initialize rules for copilot"
Project Settings Commands
To get comprehensive project settings:
- "get project settings"
- "show settings"
- "project settings"
Context Analysis Commands
To analyze project documentation:
- "prime context"
- "analyze project context"
- "build context"
Thinking Commands
To record a thought:
- "think about [your thought here]"
Usage Examples
Here are some examples of how to use these commands:
Using from Command Line
You can also use natural language commands with the MCP Agile Flow CLI:
Error Handling
If the system cannot recognize a command, it will return an error message explaining that no command was detected and suggesting to use more specific wording.
Extending Commands
The natural language command detection is implemented in utils.py
using regular expressions. To add support for new command patterns, add appropriate regex patterns to the detect_mcp_command
function.
Development
To set up for development:
- Clone the repository:
- Create a virtual environment:
- Install development dependencies:
- Run tests:
- Common Makefile commands:
License
This project is licensed under the MIT License - See LICENSE file for details.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Tools
A comprehensive system for managing AI-assisted agile development workflows with a modern, resource-based API using FastMCP.
Related MCP Servers
- -securityFlicense-qualityA production-ready MCP server built with FastAPI, providing an enhanced tool registry for creating, managing, and documenting AI tools for Large Language Models (LLMs).Last updated -13Python
- AsecurityAlicenseAqualityProvides tools for interacting with Targetprocess, a project management and agile planning platform, enabling AI assistants to search, create, and update project entities with proper validation.Last updated -54TypeScriptMIT License
- -securityAlicense-qualityA server implementation of the Model Context Protocol (MCP) for managing development workflow with features like project management, task tracking, and QA review support.Last updated -JavaScriptAGPL 3.0
- -securityFlicense-qualityA FastAPI-based implementation of the Model Context Protocol that enables standardized interaction between AI models and development environments, making it easier for developers to integrate and manage AI tasks.Last updated -5PythonMIT License