
mobile mcp
一个支持移动端使用的 MCP 工具后端和前端界面。
Repository Info
About This Server
一个支持移动端使用的 MCP 工具后端和前端界面。
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
Mobile-Mcp a backend and frontend ui to use mcp tools even in a mobile devices.
How Tool Calling Works in This Implementation
When a user sends a message through the API, the following process happens:
Initial LLM Processing:
- The user message is stored in the database
- The message along with chat history is sent to the selected model
- The model processes the message and may decide to use tools
Tool Execution:
If the model includes tool calls in its response, the application:
- Identifies each requested tool
- Executes each tool with the provided arguments
- Records the tool execution and results in the database
- Creates tool call messages with the results
Final Response Generation:
- After tool execution, the tool results are fed back to the model
- The model generates a final response that incorporates the tool results
- This final response is stored in the database and returned to the user
Things to implement next :
- just deploy this backend first and then it will work properly
- or create a expo mobile app with server side option in expo and deploy it to eas
- streaming the messages with sse
- creating all in one script for termux to directly executes all installation steps
- improving overall ui
- Yeah, improve this documentation
Installation Steps :
install termux from here : Termux
In termux
termux-setup-storage
pkg update
pkg install nodejs
pkg install git
git clone https://github.com/sujal011/mobile-mcp
cd mcp-backend
npm install
Create a postgres db on neon.tech or supabase and get the database url
in the .env file update the database url
mv .env.example .env
enter the api keys if you dont have still write something
npm db:generate
npm db:push
Now to use tavily mcp server you can :
npm install tavily-mcp@0.1.4
create a tavily api key from here
edit the .env file
TAVILY_API_KEY = <your-tavily-api-key
edit your mcponfig.json file (Note: you will always need to rerun the backend whenver you change the mcpconfig.json)
nano mcpconfig.json
{
"mcpServers": {
"tavily-mcp": {
"command": "node",
"args": [
"node_modules/tavily-mcp/build/index.js"
]
}
}
}
Note : the npx command does not work so if you have any mcp server which has npx parameter in it you can simply npm install it and use it with the example like above and if it requires the api key add it to the .env then run thr dev server
npm run dev
(inside the mcp-backend folder)
Quick Start
Clone the repository
git clone https://github.com/sujal011/mobile-mcpInstall dependencies
cd mobile-mcp
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.