Devplan MCP Server
D

Devplan MCP Server

A development planning server based on the MCP protocol, integrating the ClaudeCode - DevPlanBuilder methodology into Claude Code. Through a workflow of structured interviews, detailed plan generation, Haiku execution, and Sonnet verification, it transforms ideas into executable development plans, including experience learning and GitHub issue fixing functions.
2 points
6.4K

What is the DevPlan MCP Server?

DevPlan is an intelligent development planning server based on the Model Context Protocol (MCP), specifically designed for Claude Code. It addresses common issues in AI programming assistants such as context loss, step skipping, and code inconsistency. Through a structured workflow, DevPlan transforms your project ideas into detailed, executable development plans that can be accurately executed even by small models like Claude Haiku.

How to use DevPlan?

Using DevPlan is very simple: just tell it in Claude Code, 'Use devplan to help me build [your project idea]'. DevPlan will automatically guide Claude through the entire development process: from requirement gathering, plan formulation, to code execution and verification, and finally summarize lessons learned. The entire process is fully automated and does not require manual configuration.

Use cases

DevPlan is particularly suitable for the following scenarios: 1. New project development - Build applications from scratch. 2. Feature expansion - Add new features to existing projects. 3. Problem fixing - Transform GitHub issues into repair tasks. 4. Code refactoring - Systematically improve code structure. 5. Team collaboration - Ensure consistency and repeatability in the development process.

Main features

Structured development methodology
Built - in complete development process: planning → execution → verification → learning, ensuring that each step is carried out in an orderly manner.
Haiku executable plan
Generate extremely detailed development plans that can be accurately understood and executed even by small models.
Lessons learned system
Automatically capture problems from the verification process and apply the experience to future plans to avoid repeated mistakes.
GitHub issue fixing
Directly transform GitHub issues into structured repair tasks, including detailed subtasks and verification steps.
Technical conflict detection
Automatically detect incompatible technology choices in the project and issue early warnings for potential problems.
Automatic agent generation
Automatically generate specialized execution agents (Haiku) and verification agents (Sonnet) for your project.
Content drift detection
Detect outdated inline guidance to ensure that development guidance is always up - to - date.
Error recovery guidance
When an error occurs during execution, provide specific recovery steps and solutions.
Advantages
Maintain development context - Completely save the development status and plan between different sessions.
Ensure code consistency - Detailed plans ensure that each execution follows the same standards.
Proactive error prevention - Verification agents actively look for potential problems before code execution.
Continuous learning and improvement - The lessons learned system continuously optimizes the development process.
Seamless integration - Deeply integrated with Claude Code and GitHub, no additional configuration is required.
Lower the technical threshold - Non - technical users can also complete complex projects through structured guidance.
Limitations
Requires a Claude Code environment - Can only be used in Claude Code that supports MCP.
Learning curve - Need to understand the workflow and tools of DevPlan.
Plan generation time - Generating detailed plans may take some time.
Dependent on model capabilities - The execution quality is affected by the capabilities of the underlying AI model.
Specific scenario optimization - Mainly targeted at software development scenarios and may not be applicable in other fields.

How to use

Install the DevPlan MCP server
Add the DevPlan MCP server in Claude Code
Start a new project
Tell Claude what you want to build, and DevPlan will automatically guide the entire process
Answer requirement questions
Claude will ask project requirements through the devplan_interview_questions tool. Please answer them one by one.
View and approve the plan
DevPlan will generate a detailed development plan, and you can view and confirm it.
Monitor the execution progress
Use the progress tracking tool to view the project status
Handle GitHub issues
If there are GitHub issues to be fixed, you can transform them into tasks

Usage examples

Build a CLI tool
Create a command - line tool for managing dotfiles, supporting synchronization, backup, and version control.
Fix a production - environment bug
Transform a production - environment problem report on GitHub into specific repair tasks.
Refactor an existing codebase
Improve the code structure of an existing project to enhance maintainability and performance.
Add a new feature module
Add user authentication and authorization functions to an existing application.

Frequently Asked Questions

Does DevPlan require additional payment?
Which programming languages and frameworks does DevPlan support?
What if there are errors in the plan generated by DevPlan?
How large a project can DevPlan handle?
How to view the learning results of DevPlan?
Does DevPlan support team collaboration?
What if my network cannot access Cloudflare Workers?
Will DevPlan store my project code?

Related resources

DevPlanBuilder Methodology Documentation
The core methodology and design concept behind DevPlan
Model Context Protocol Official Website
Official documentation and specifications of the MCP protocol
Cloudflare Workers Documentation
Documentation for the operating platform of the DevPlan server
Claude Code Official Documentation
Claude Code usage guide and MCP integration instructions
GitHub Issues API Documentation
GitHub API reference for the issue_to_task function
DevPlan Example Projects
Actual project examples using the DevPlan methodology

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "devplan": {
      "type": "sse",
      "url": "https://devplan-mcp-server.mike-c63.workers.dev/sse"
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
8.9K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.4K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.2K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.4K
4 points
P
Paperbanana
Python
9.2K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
9.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
8.2K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.9K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.1K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.9K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
79.1K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
36.6K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
36.8K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
68.6K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
23.1K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
102.5K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase