SOL Claimer MCP Server

SOL Claimer MCP Server

An MCP server that enables AI assistants to analyze Solana wallets for empty or low-value token accounts. It allows users to identify opportunities to recover SOL rent by closing or burning these accounts through the SOL Claimer API.

Category
Visit Server

README

SOL Claimer MCP Server

npm version License: MIT Node.js Version CI

A Model Context Protocol (MCP) server that provides seamless integration between LLM applications (ChatGPT, Claude, etc.) and the SOL Claimer API. This server enables AI assistants to analyze Solana token accounts and help users recover rent from empty and low-value token accounts.

Features

  • āœ… Three Powerful Tools:

    1. analyze_empty_accounts - Find and recover rent from empty token accounts
    2. analyze_burnable_accounts - Identify low-value tokens (<$1) to burn and close
    3. get_how_it_works - Learn about SOL Claimer functionality
  • šŸ”„ Real-time API Integration - Direct connection to SOL Claimer API

  • šŸ›”ļø Error Handling - Graceful error management and user-friendly messages

  • šŸ“Š Rich Response Formatting - Detailed, readable analysis results

Prerequisites

  • Node.js 18+ (tested on v20+)
  • npm 10+
  • SOL Claimer API running locally or accessible via network
  • Environment variable SOLCLAIMER_API_URL (optional, defaults to http://localhost:3000)

Installation

Option 1: Install from npm (Recommended)

# Install globally
npm install -g @solclaimer/mcp

# Or install locally in your project
npm install @solclaimer/mcp

Option 2: Install from source

# Clone the repository
git clone https://github.com/solclaimer/mcp.git
cd mcp

# Install dependencies
npm install

# Build the project
npm run build

# Start the server
npm start

Configuration

Environment Variables

Optionally set the SOL Claimer API URL:

export SOLCLAIMER_API_URL=http://localhost:3000

If not set, defaults to http://localhost:3000.

Development

# Watch TypeScript changes and run
npm run dev

# Format code
npm run format

# Lint code
npm run lint

Tools

1. analyze_empty_accounts

Analyzes a Solana wallet for empty token accounts that can be closed to recover rent.

Parameters:

  • wallet_address (string, required): The Solana wallet address to analyze

Response:

  • accountsToClose - Number of empty accounts found
  • totalSol - Total SOL available for recovery

2. analyze_burnable_accounts

Analyzes a wallet for token accounts with balances worth less than $1 USD that can be burned and closed.

Parameters:

  • wallet_address (string, required): The Solana wallet address to analyze

Response:

  • accountsToBurn - Number of burnable accounts found
  • totalSol - Total SOL available for recovery
  • totalUsdValue - Combined USD value of all burnable tokens
  • accountDetails - Array of detailed account information including:
    • Token name and symbol
    • Amount and USD value
    • Rent (in lamports)
    • Contract verification status

3. get_how_it_works

Returns documentation about SOL Claimer features and capabilities.

Parameters: None

Response:

  • Information about SOL Claimer features
  • Description of how it works
  • Website link

Example Usage with Claude

User: "Can you analyze my Solana wallet at 7cvkjYAkUYs4W8XcXsca7cBrEGFeSUjeZmKoNBvEwyri?"

Claude: [Uses analyze_empty_accounts and analyze_burnable_accounts tools]
"Based on the analysis, I found:
- 5 empty token accounts: 0.0101964 SOL can be recovered
- 12 burnable accounts: 0.0244713 SOL can be recovered (worth $0.52)
..."

Integration with LLM Platforms

Claude (via claude.ai or Claude API)

  1. Create a Claude project with this MCP server
  2. Configure the MCP server in your Claude settings
  3. Claude will automatically use the available tools when analyzing Solana wallets

ChatGPT / OpenAI

  1. Set up a custom integration pointing to this MCP server
  2. Configure as a tool/action in your OpenAI integration
  3. Use natural language to analyze wallets

Generic MCP Client Integration

Any MCP-compatible client can connect to this server using:

{
  "mcpServers": {
    "solclaimer": {
      "command": "node",
      "args": ["/path/to/dist/index.js"],
      "env": {
        "SOLCLAIMER_API_URL": "http://localhost:3000"
      }
    }
  }
}

Architecture

Project Structure

src/
ā”œā”€ā”€ index.ts          # Main MCP server implementation
tsconfig.json         # TypeScript configuration
package.json          # Dependencies and scripts

Key Components

  1. SolClaimerApiClient - Handles communication with the SOL Claimer API
  2. MCP Server - Exposes three tools via the Model Context Protocol
  3. Response Formatters - Transform API responses into readable text

Troubleshooting

Connection refused error

  • Ensure SOL Claimer API is running on the configured SOLCLAIMER_API_URL
  • Default: http://localhost:3000
  • Check firewall and port accessibility

Invalid wallet address

  • Verify the Solana wallet address format (44-character base58 string)
  • Examples: 7cvkjYAkUYs4W8XcXsca7cBrEGFeSUjeZmKoNBvEwyri

API timeout

  • Check network connectivity to the SOL Claimer API
  • Increase timeout if API is slow (edit timeout in SolClaimerApiClient)
  • Check if Solana RPC endpoint is accessible

Performance

  • Requests include 30-second timeout to prevent hanging
  • No caching at MCP layer (respects API caching)
  • Suitable for real-time analysis

License

UNLICENSED

Links

  • SOL Claimer Website: https://solclaimer.app/
  • Model Context Protocol: https://modelcontextprotocol.io/
  • TypeScript SDK: https://github.com/modelcontextprotocol/typescript-sdk

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured