DevForge-MCP
A production-ready MCP server that enables AI assistants to intelligently understand, analyze, edit, navigate, and review software projects with multi-workspace support, Git integration, and semantic search.
README
๐ DevForge-MCP
<p align="center"> <strong>A Production-Ready Model Context Protocol (MCP) Server for AI-Assisted Software Development</strong> </p>
<p align="center"> Empower AI assistants like ChatGPT and Claude with intelligent code understanding, multi-project workspaces, semantic search, Git integration, architecture analysis, and safe code editing. </p>
<p align="center">
</p>
โจ Overview
DevForge-MCP is a production-ready Model Context Protocol (MCP) server that enables AI coding assistants to intelligently understand, analyze, review, edit, and navigate software projects.
Unlike a traditional file server, DevForge-MCP builds an intelligent representation of your codebase, detects project architecture, manages multiple workspaces, integrates with Git, performs semantic code search, and exposes 44 developer tools through the latest Streamable HTTP MCP transport.
It is designed to work with modern AI assistants that support MCP, providing them with rich contextual understanding of your projects.
โจ Key Features
๐ง AI Code Intelligence
- Architecture detection
- Semantic code search
- Symbol lookup
- Dependency graph generation
- Context-aware navigation
- Duplicate code detection
๐ Workspace Management
- Multi-project support
- Project switching
- Automatic indexing
- Persistent project memory
- Incremental cache rebuilding
๐ธ Dashboard

โ Safe Code Editing
- Patch files
- Replace methods
- Insert methods/classes
- Rename symbols
- Delete methods
- Multi-file editing
๐ฟ Git Integration
- Git status
- Commit changes
- Branch management
- Checkout branches
- Git history
- Diff inspection
๐ Code Review
- Code smell detection
- Architecture review
- Refactoring suggestions
- Build error explanation
- Project review
โก Modern MCP
- Streamable HTTP
- JSON-RPC 2.0
- Stateless transport
- OpenAI Secure Tunnel compatible
- Latest MCP SDK
๐ Architecture
AI Assistant
(ChatGPT / Claude)
โ
โผ
Model Context Protocol (MCP)
โ
Streamable HTTP Transport
โ
โผ
DevForge-MCP Server
โ
โโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโ
โ โ โ
โผ โผ โผ
Code Intelligence Git Engine Workspace Manager
โ โ โ
โโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโ
โผ
Local Project Files
๐ Core Capabilities
- Intelligent codebase indexing
- Multi-project workspaces
- Architecture detection
- Semantic code search
- Safe editing operations
- Git automation
- Build automation
- Code review
- Security inspection
- Project memory
- Dashboard
- Status API
๐ฆ Technology Stack
- Node.js
- Express.js
- JavaScript
- Model Context Protocol SDK (v1.29+)
- Streamable HTTP
- Docker
- Railway
- Render
๐ Project Structure
DevForge-MCP
โ
โโโ lib/
โ โโโ architecture.js
โ โโโ buildTools.js
โ โโโ cache.js
โ โโโ codeIntel.js
โ โโโ editing.js
โ โโโ fsTools.js
โ โโโ gitTools.js
โ โโโ indexer.js
โ โโโ logger.js
โ โโโ reviewTools.js
โ โโโ security.js
โ โโโ state.js
โ
โโโ mcp/
โ โโโ handlers.js
โ โโโ server.js
โ โโโ tools.js
โ โโโ transport.js
โ
โโโ public/
โ
โโโ tests/
โ
โโโ server.js
โโโ package.json
โโโ Dockerfile
โโโ README.md
๐ Getting Started
Clone Repository
git clone https://github.com/Sanket2329/DevForge-MCP.git
cd DevForge-MCP
Install Dependencies
npm install
Start Server
npm start
Server Endpoints
| Endpoint | Description |
|---|---|
/mcp |
MCP Endpoint |
/dashboard |
Web Dashboard |
/status |
Server Status |
โ Environment Variables
| Variable | Default | Purpose |
|---|---|---|
| PROJECT_PATH | Sample project | Initial project to index |
| WORKSPACE_ROOT | Parent directory | Workspace containing projects |
| PORT | 3000 | HTTP server port |
| MCP_API_KEY | unset | Protects REST API endpoints |
| LOG_LEVEL | info | Logging level |
๐งฐ Developer Tool Inventory
Workspace
- list_projects
- select_project
- get_current_project
- refresh_index
Code Navigation
- get_project_files
- get_file_content
- get_full_codebase
- search_codebase
- get_architecture
- get_dependency_graph
- get_context
Safe Editing
- write_file
- write_multiple_files
- patch_file
- replace_method
- insert_method
- insert_class
- rename_symbol
- delete_method
Code Intelligence
- find_symbol
- find_class
- find_method
- find_interface
- find_references
- find_unused_files
- find_duplicate_code
Git
- git_status
- git_diff
- git_log
- git_checkout
- create_branch
- commit_changes
- show_untracked_files
Review
- review_file
- review_project
- find_code_smells
- review_architecture
- suggest_refactoring
- explain_build_error
Memory
- add_conversation_turn
- get_conversation_history
- add_project_note
- get_project_memory
๐งช Testing
The project has been validated with:
โ SDK Import Tests
โ Streamable HTTP Transport
โ JSON-RPC Request Handling
โ MCP Tool Registration
โ Tool Discovery (44 Tools)
โ Integration Tests
โ OpenAI Secure Tunnel
โ Workspace Switching
โ Codebase Indexing
๐ Streamable HTTP Migration
DevForge-MCP has been migrated from the legacy Server-Sent Events (SSE) transport to the latest Streamable HTTP transport.
Migration Highlights
- Removed legacy SSE transport
- Stateless request handling
- JSON-RPC 2.0 compliance
- Modern MCP SDK compatibility
- OpenAI Secure Tunnel support
- Improved scalability
๐ Deployment
DevForge-MCP supports deployment using:
- Docker
- Railway
- Render
Deployment configuration files included:
- Dockerfile
- railway.toml
- render.yaml
For deployment instructions, see:
DEPLOYMENT.md
๐ Connecting AI Assistants
MCP Endpoint
https://your-domain.com/mcp
Compatible with:
- ChatGPT (Developer Mode)
- Claude Desktop
- MCP-compatible clients
Authentication:
No Authentication
unless configured otherwise.
โ Known Limitations
- Architecture detection is heuristic-based.
- Code review is pattern-based rather than compiler-backed.
- Duplicate code detection uses hash comparison instead of semantic analysis.
- Editing operations rely on syntax heuristics for different languages.
๐ Roadmap
- Vector Search
- Embedding Support
- RAG Integration
- Plugin System
- Authentication
- GitHub Actions CI/CD
- Performance Metrics
- Language Server Protocol Integration
๐ค Contributing
Contributions are welcome.
- Fork the repository.
- Create a feature branch.
- Commit your changes.
- Submit a Pull Request.
๐ License
This project is licensed under the MIT License.
๐จโ๐ป Author
Sanket Shakya
- GitHub: https://github.com/Sanket2329
โญ Support
If you find DevForge-MCP useful, consider giving the repository a โญ Star on GitHub.
It helps others discover the project and supports future development.
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.
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.
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.
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.