Documentation

What is Solana MCP?

Solana MCP is a Model Context Protocol (MCP) server that provides onchain tools for Claude AI, allowing it to interact with the Solana blockchain through a standardized interface. This implementation is based on the Solana Agent Kit and enables AI agents to perform blockchain operations seamlessly.

What is the Model Context Protocol?

The Model Context Protocol (MCP) is a standardized interface for AI models to interact with tools and resources. It allows AI models like Claude to:

  • Discover available tools and capabilities
  • Access resources and information
  • Execute operations through standardized interfaces
  • Handle responses in a consistent format

Tools Reference

GET_ASSET

Retrieve information about a Solana asset/token

// Example Usage
GET_ASSET tokenMint="So11111111111111111111111111111111111111112"

DEPLOY_TOKEN

Deploy a new token on Solana

// Example Usage
DEPLOY_TOKEN name="My Token" symbol="MT" decimals=9

GET_PRICE

Fetch price information for tokens

// Example Usage
GET_PRICE symbol="SOL"

WALLET_ADDRESS

Get the wallet address

// Example Usage
WALLET_ADDRESS

BALANCE

Check wallet balance

// Example Usage
BALANCE

TRANSFER

Transfer tokens between wallets

// Example Usage
TRANSFER recipient="9x4uFyxEYhYvmcLdsWHtKnKZhNfSrfJ3cn5oiRKj9KYV" amount=0.1 token="SOL"

MINT_NFT

Create and mint new NFTs

// Example Usage
MINT_NFT name="My NFT" uri="https://example.com/metadata.json"

TRADE

Execute token trades

// Example Usage
TRADE side="buy" token="RAY" amount=10 payWith="SOL"

REQUEST_FUNDS

Request funds (useful for testing/development)

// Example Usage
REQUEST_FUNDS amount=1 network="devnet"

RESOLVE_DOMAIN

Resolve Solana domain names

// Example Usage
RESOLVE_DOMAIN domain="myname.sol"

GET_TPS

Get current transactions per second on Solana

// Example Usage
GET_TPS

Security Considerations

  • Keep your private key secure and never share it
  • Use environment variables for sensitive information
  • Consider using a dedicated wallet for AI agent operations
  • Regularly monitor and audit AI agent activities
  • Test operations on devnet/testnet before mainnet

Resources