
https://github.com/Streen9/react-mcp
react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts
Tools
read-file
Read the contents of a file
create-react-app
Create a new React application
run-react-app
Run a React application in development mode
run-command
Run a terminal command
get-process-output
Get the output from a running or completed process
stop-process
Stop a running process
list-processes
List all running processes
edit-file
Create or edit a file
install-package
Install a npm package in a project
README
React MCP (Model Context Protocol)
A powerful server implementation that enables Claude AI to interact with React applications through the Model Context Protocol.
<a href="https://glama.ai/mcp/servers/xsjsdumc7x"> <img width="380" height="200" src="https://glama.ai/mcp/servers/xsjsdumc7x/badge" alt="https://github.com/Streen9/react-mcp MCP server" /> </a>
Sample Usage
Overview
React MCP provides a bridge between Claude AI and the React ecosystem, allowing Claude to:
- Create new React applications
- Run React development servers
- Manage files and directories
- Install npm packages
- Execute terminal commands
- Track and manage long-running processes
This server implements the Model Context Protocol, providing Claude with the ability to perform real-world actions in the development environment.
Features
-
React Project Management
- Create new React applications with optional templates
- Run development servers
- Manage dependencies
-
File Operations
- Read and write files
- Edit React components and configuration
-
Process Management
- Start and monitor long-running processes
- Track process output in real-time
- Terminate processes when needed
-
Command Execution
- Run arbitrary terminal commands
- Install npm packages
- Execute development tasks
-
Comprehensive Logging
- Detailed JSON and text logs
- Process tracking with timestamps
- Execution history
Installation
Installing via Smithery
To install React MCP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @Streen9/react-mcp --client claude
Manual Installation
- Clone this repository
- Install dependencies:
npm install
Usage
Add this in claude_desktop_config
:
{
"mcpServers": {
"react-mcp": {
"command": "node",
"args": [
"C:/Users/kalip/OneDrive/Desktop/react-mcp/index.js"
]
},
}
}
The server runs on the stdio transport, allowing it to be used with Desktop Claude APP as a Model Context Protocol tool.
Available Tools
create-react-app
Creates a new React application.
Parameters:
name
(required): Name of the React apptemplate
(optional): Template to use (e.g., typescript, cra-template-pwa)directory
(optional): Base directory to create the app in (defaults to home directory)
run-react-app
Runs a React application in development mode.
Parameters:
projectPath
(required): Path to the React project folder
run-command
Runs a terminal command.
Parameters:
command
(required): Command to executedirectory
(optional): Directory to run the command in (defaults to current directory)
get-process-output
Gets the output from a running or completed process.
Parameters:
processId
(required): ID of the process to get output from
stop-process
Stops a running process.
Parameters:
processId
(required): ID of the process to stop
list-processes
Lists all running processes.
edit-file
Creates or edits a file.
Parameters:
filePath
(required): Path to the file to editcontent
(required): Content to write to the file
read-file
Reads the contents of a file.
Parameters:
filePath
(required): Path to the file to read
install-package
Installs a npm package in a project.
Parameters:
packageName
(required): Name of the package to install (can include version)directory
(optional): Directory of the project (defaults to current directory)dev
(optional): Whether to install as a dev dependency
check-installation-status
Checks the status of a package installation process.
Parameters:
processId
(required): ID of the installation process to check
Logging
The server maintains detailed logs in the logs
directory:
react-mcp-logs.json
: Structured JSON logsreact-mcp-logs.txt
: Human-readable text logs
Architecture
The server uses the following key components:
- Model Context Protocol SDK: For communication with Claude AI
- StdioServerTransport: For I/O through standard input/output
- Zod: For schema validation and type safety
- Child Process: For spawning and managing external processes
License
MIT
Author
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
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.