Solana Agent logo

Solana Agent

Organization
sendaifun

A Model Context Protocol server for interacting with the Solana blockchain, powered by the Solana Agent Kit (https://github.com/sendaifun/solana-agent-kit)

Publishersendaifun
Repositorysolana-mcp
LanguageShell
Forks
49
Stars
159
Available tools
0
Transport typestdio
Categories
LicenseApache-2.0
Links
  • Connect tools to AI workflows

    Solana Agent exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    159 stars and 49 forks from the linked repository.

Solana Agent Kit MCP Server

npm version License: ISC Check on Phala

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.

Overview

This MCP server extends Claude's capabilities by providing tools to:

  • Interact with Solana blockchain
  • Execute transactions
  • Query account information
  • Manage Solana wallets

The server implements the Model Context Protocol specification to standardize blockchain interactions for AI agents.

Prerequisites

  • Node.js (v16 or higher)
  • pnpm (recommended), npm, or yarn
  • Solana wallet with private key
  • Solana RPC URL (mainnet, testnet, or devnet)

Installation

Option 1: Quick Install (Recommended)

bash
# Download the installation script
curl -fsSL https://raw.githubusercontent.com/sendaifun/solana-mcp/main/scripts/install.sh -o solana-mcp-install.sh

# Make it executable and run
chmod +x solana-mcp-install.sh && ./solana-mcp-install.sh --backup

This will start an interactive installation process that will guide you through:

  • Setting up Node.js if needed
  • Configuring your Solana RPC URL and private key
  • Setting up the Claude Desktop integration

Option 2: Install from npm ( recommend for clients like Cursor/Cline)

bash
# Install globally
npm install -g solana-mcp

# Or install locally in your project
npm install solana-mcp

Option 3: Build from Source

  1. Clone this repository:
bash
git clone https://github.com/sendaifun/solana-mcp
cd solana-mcp
  1. Install dependencies:
bash
pnpm install
  1. Build the project:
bash
pnpm run build

Configuration

Environment Setup

Create a .env file with your credentials:

env
# Solana Configuration
SOLANA_PRIVATE_KEY=your_private_key_here
RPC_URL=your_solana_rpc_url_here
OPENAI_API_KEY=your_openai_api_key # OPTIONAL

Integration with Claude Desktop

To add this MCP server to Claude Desktop, follow these steps:

  1. Locate the Claude Desktop Configuration File

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • Linux: ~/.config/Claude/claude_desktop_config.json
  2. Add the Configuration Create or edit the configuration file and add the following JSON:

    If you installed via npm (Option 1):

    json
    {
      "mcpServers": {
        "solana-mcp": {
          "command": "npx",
          "args": ["solana-mcp"],
          "env": {
            "RPC_URL": "your_solana_rpc_url_here",
            "SOLANA_PRIVATE_KEY": "your_private_key_here",
            "OPENAI_API_KEY": "your_openai_api_key"  // OPTIONAL
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }

    If you built from source (Option 2):

    json
    {
      "mcpServers": {
        "solana-mcp": {
          "command": "node",
          "args": ["/path/to/solana-mcp/build/index.js"],
          "env": {
            "RPC_URL": "your_solana_rpc_url_here",
            "SOLANA_PRIVATE_KEY": "your_private_key_here",
            "OPENAI_API_KEY": "your_openai_api_key"  // OPTIONAL
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }
  3. Restart Claude Desktop After making these changes, restart Claude Desktop for the configuration to take effect.

Project Structure

solana-agent-kit-mcp/
ā”œā”€ā”€ src/
│   ā”œā”€ā”€ index.ts          # Main entry point
ā”œā”€ā”€ package.json
└── tsconfig.json

Available Tools

The MCP server provides the following Solana blockchain tools:

  • GET_ASSET - Retrieve information about a Solana asset/token
  • DEPLOY_TOKEN - Deploy a new token on Solana
  • GET_PRICE - Fetch price information for tokens
  • WALLET_ADDRESS - Get the wallet address
  • BALANCE - Check wallet balance
  • TRANSFER - Transfer tokens between wallets
  • MINT_NFT - Create and mint new NFTs
  • TRADE - Execute token trades
  • REQUEST_FUNDS - Request funds (useful for testing/development)
  • RESOLVE_DOMAIN - Resolve Solana domain names
  • GET_TPS - Get current transactions per second on Solana

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

Troubleshooting

If you encounter issues:

  1. Verify your Solana private key is correct
  2. Check your RPC URL is accessible
  3. Ensure you're on the intended network (mainnet, testnet, or devnet)
  4. Check Claude Desktop logs for error messages
  5. Verify the build was successful

Dependencies

Key dependencies include:

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License.

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "solana-mcp": {
      "command": "npx",
      "args": [
        "solana-mcp"
      ],
      "env": {
        "RPC_URL": "your_solana_rpc_url_here",
        "SOLANA_PRIVATE_KEY": "your_private_key_here",
        "OPENAI_API_KEY": "your_openai_api_key"
      }
    }
  }
}

Use Solana Agent MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Solana Agent is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Solana Agent as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Solana Agent MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "solana-agent": {
      "command": "npx",
      "args": [
        "-y",
        "solana-mcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Solana Agent MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Solana Agent MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Solana Agent to help me with this task?
Solana Agent
Sure. I read it.
Here is what I found using Solana Agent.

Frequently asked questions

What is the Solana Agent MCP server used for?

Solana Agent is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Solana Agent MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Solana Agent with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Solana Agent MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Solana Agent connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Solana Agent MCP to TypingMind?

Solana Agent runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Solana Agent MCP provide in TypingMind?

Solana Agent exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Solana Agent MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Solana Agent requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter šŸ‘‡