mcp-micromanage
Controls coding agents by enforcing structured implementation plans with PRs and commits as work units, requiring user review at each commit checkpoint to prevent agents from going off track. Includes a visualization dashboard for tracking progress in real-time.
README
mcp-micromanage
Control your coding agent colleague who tends to go off track.
If sequentialthinking is a dynamic formulation and externalization of thought workflows, this tool is a dynamic formulation and externalization of development task flows.
Motivation
Challenges with Coding Agents
- Coding agents often make modifications beyond what they're asked to do
- Assuming cursor+claude
- They struggle to request user feedback at key decision points during implementation
- Work plans and progress tracking can be challenging to visualize and monitor
Solution
- Commit and PR-based Work Plans: Force implementation plans that break down tickets into PRs and commits as the minimum units of work
- Forced Frequent Feedback: Enforce user reviews at the commit level, creating natural checkpoints for feedback
- Visualization: Instantly understand the current work plan and implementation status through a local React app
tool
- plan: Define your implementation plan with PRs and commits
- track: Monitor progress and current status of all work items
- update: Change status as work progresses, with mandatory user reviews
Visualization Dashboard
The project includes a React-based visualization tool that provides:
- Hierarchical view of PRs and commits
- Real-time updates with auto-refresh
- Status-based color coding
- Zoom and pan capabilities
Getting Started
Headless(mcp tool only)
- Add to your mcp json
{
"mcpServers": {
"micromanage": {
"command": "npx",
"args": [
"-y",
"@yodakeisuke/mcp-micromanage"
]
}
}
}
- (Highly recommended) Add the following
.mdcs to your project
(Can be adjusted to your preference)
With Visualisation
-
clone this repository
-
Add to your mcp json
{
"mcpServers": {
"micromanage": {
"command": "node",
"args": [
"[CLONE_DESTINATION_PATH]/sequentialdeveloping/dist/index.js"
]
}
}
}
- build server
npm install
npm run build
- run frontend
cd visualization/
npm install
npm run dev
License
This project is licensed under the MIT License - see the LICENSE file for details.
Third-Party Software
This project uses the following third-party software:
- MCP TypeScript SDK: Licensed under the MIT License. Copyright © 2023-2025 Anthropic, PBC.
Acknowledgments
- Built with MCP (Model Context Protocol)
- Maintained by yodakeisuke
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.