About Aptos MCP Server
Aptos MCP Server helps developers explore Aptos documentation and build full-stack Aptos blockchain applications. It includes project scaffolding, component generation, Move contract testing, and TypeScript ABI generation.
Key features
- 01Browse and search Aptos documentation
- 02Create full-stack, contract, or client projects
- 03Generate project components
- 04Test Aptos Move contracts
- 05Generate TypeScript ABI interfaces
Use cases
- 01Look up Aptos and Move documentation
- 02Start an Aptos application or contract
- 03Test a Move contract
- 04Create TypeScript bindings for a Move contract
MCP support
The MCP server exposes documentation browsing and search, Aptos project and component creation, contract testing, and ABI generation to connected clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAptos MCP Server
A Model Context Protocol (MCP) server for interacting with Aptos documentation and creating full-stack Aptos blockchain applications.
Features
- 🔍 Browse and search Aptos documentation
- 🔧 Create new Aptos projects (fullstack, contract, or client)
- 🧩 Generate components for Aptos projects
- 🧪 Test Aptos Move contracts
- 📜 Generate TypeScript ABI interfaces for Move contracts
Installation
Prerequisites
- Python 3.10 or later
- Node.js and npm
- Aptos CLI (for some tooling features)
Setup
- Install the mcp package:
uv add "mcp[cli]"
# or
pip install "mcp[cli]"
- Clone this repository:
git clone https://github.com/yourusername/aptos-mcp-server.git
cd aptos-mcp-server
- Install dependencies:
uv add httpx
# or
pip install httpx
- (Optional) Set GitHub token for increased API rate limits:
export GITHUB_TOKEN=your_github_token
Using with Claude Desktop
-
Install Claude Desktop from claude.ai/download
-
Add the Aptos MCP Server to your Claude Desktop configuration:
mcp install aptos_mcp_server.py
Or manually edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"aptos-dev": {
"command": "uv",
"args": [
"--directory",
"/path/to/aptos-mcp-server",
"run",
"aptos_mcp_server.py"
]
}
}
}
- Restart Claude Desktop
Development
Run the server in development mode with the MCP Inspector:
mcp dev aptos_mcp_server.py
Usage
Once connected to Claude Desktop, you can:
Browse Aptos Documentation
Ask Claude to browse through the Aptos documentation repository:
- "Show me the Aptos documentation structure"
- "Find information about Move modules in the Aptos docs"
- "Get me the Table implementation documentation"
Create New Projects
Ask Claude to set up new Aptos projects:
- "Create a new Aptos full-stack project called 'my-first-dapp'"
- "Generate a Move smart contract for a marketplace"
- "Set up a client-only Aptos project"
Generate Components
Ask Claude to generate components for your Aptos projects:
- "Generate a React component for connecting to Aptos wallet"
- "Create a Move table for storing user profiles"
- "Make a client function for querying contract data"
Test and Generate ABIs
Ask Claude to test contracts and generate interfaces:
- "Test my Aptos contract at ~/projects/my-dapp/move"
- "Generate TypeScript bindings for my Move contract"
Example Queries
- "Browse through the Aptos documentation"
- "Search the Aptos docs for 'table'"
- "Create a new Aptos fullstack project called 'nft-marketplace'"
- "Generate a Move module for a token contract"
- "Create a React component for wallet connection"
- "Generate TypeScript ABI for my contract"
- "Test my contract's withdraw function"
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.