loading…
Search for a command to run...
loading…
Enables AI models to manage decentralized storage, hosting, and NFTs via Apillon's API.
Enables AI models to manage decentralized storage, hosting, and NFTs via Apillon's API.
Welcome to the Apillon MCP Server repository. This project implements a server using the Model Context Protocol (MCP) to provide modules for Storage, Hosting, and NFT functionalities.
The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.
MCP helps you build agents and complex workflows on top of LLMs. LLMs frequently need to integrate with data and tools, and MCP provides:
For more information, visit the Model Context Protocol Introduction.
This project is developed by Apillon and provides a server implementation for the following modules:
The Storage module provides comprehensive file management capabilities:
The Hosting module enables web application deployment:
The NFT module provides comprehensive NFT management:
To use this MCP with the Claude LLM, follow these steps:
Install Claude for Desktop
Locate the Claude Desktop Configuration File
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.jsonCopy the configuration from claude_desktop_config.json and adjust it with your own parameters.
⚠️ Important: Make sure to modify the API key env variables and the allowed directories for the filesystem MCP.
{
"mcpServers": {
"apillon-mcp-server": {
"command": "npx",
"args": ["-y", "@apillon/mcp-server"],
"env": {
"APILLON_API_KEY": "<APILLON_API_KEY>",
"APILLON_API_SECRET": "<APILLON_API_SECRET>"
}
},
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/your-username/Desktop"
]
}
}
}
After making these changes, restart Claude Desktop for the configuration to take effect. You can now prompt Claude to perform any of the available actions using only the text chat.
Clone the repository and install the dependencies:
git clone https://github.com/Apillon/mcp-server.git
cd mcp-server
npm install
{
"mcpServers": {
"apillon-mcp-server": {
"command": "tsx",
"args": ["/full/path/to/index.ts"],
"env": {
"APILLON_API_KEY": "<APILLON_API_KEY>",
"APILLON_API_SECRET": "<APILLON_API_SECRET>"
}
}
}
}
The preferred metho to test your server is to use Claude Dekstop with the above config. Alternatively, to start the server locally, use the following command,
npm start
To build the project, run:
npm run build
We welcome contributions to the Apillon MCP Server. Please check the issues for any open tasks or bugs.
This project is licensed under the MIT License.
This MCP server is certified by MCP review
Visit our own MCP Review page
For more information, visit Apillon's website or reach out via GitHub issues.
Выполни в терминале:
claude mcp add apillon-mcp-server -- npx Web content fetching and conversion for efficient LLM usage.
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolProvides auto-configuration for setting up an MCP server in Spring Boot applications.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzНе уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai