mcpField
S
Solscan MCP Server

Solscan MCP Server

Local
github.com/bobtistaFinance0Updated 80w ago

About Solscan MCP Server

Solscan MCP Server connects the Solscan Pro API to MCP, giving AI agents access to Solana token, transaction, and DeFi activity data. Its tools cover token and wallet analysis, with filtering, sorting, and pagination.

Key features

  1. 01Query token metadata, prices, and markets
  2. 02Inspect holder distributions and liquidity pools
  3. 03Retrieve wallet tokens, NFTs, and DeFi activity
  4. 04Get transaction details and decoded actions
  5. 05Filter, sort, and paginate results

Use cases

  1. 01Analyze Solana token markets and holders
  2. 02Review wallet transactions and DeFi activity
  3. 03Track balance changes and inspect transaction instructions

MCP support

The MCP server exposes Solscan Pro API tools for token, wallet, DeFi, and transaction queries to compatible clients. A Solscan Pro API key is required.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"solscan_mcp_server": {
"command": "uvx",
"args": [
"solscan-mcp-server"
],
"env": {
"SOLSCAN_API_KEY": "<SOLSCAN_API_KEY>"
}
}
}
}
Run commanduvx solscan-mcp-server
Environment variables to set
SOLSCAN_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypisolscan-mcp-server

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Solscan MCP Server

A Model Context Protocol (MCP) server implementation for interacting with the Solscan Pro API. This server allows AI agents to fetch and analyze token, transaction, and DeFi activity data from the Solana blockchain.

Overview

This MCP server provides a bridge between AI agents and the Solscan Pro API service. It follows the best practices laid out by Anthropic for building MCP servers, allowing seamless integration with any MCP-compatible client.

Features

The server provides several essential tools for interacting with Solscan:

  1. token_meta: Get token metadata

    • Fetch comprehensive token information
    • Get name, symbol, price, market cap, etc.
  2. token_markets: Get token market data and liquidity pools

    • View market pairs and liquidity pools
    • Filter by program addresses
    • Sort and paginate results
  3. token_holders: Get token holder distribution

    • View holder balances and distribution
    • Filter by amount ranges
    • Paginate through results
  4. token_price: Get token price information

    • Historical price data
    • Filter by date range
    • Price trends and statistics
  5. token_accounts: Get token holdings for a wallet

    • List token and NFT holdings
    • Filter zero balances
    • Paginate results
  6. defi_activities: Get DeFi activities for a wallet

    • Filter by activity type and platform
    • Sort by time or other metrics
    • Comprehensive activity details
  7. balance_change: Get balance change activities

    • Track token balance changes
    • Filter by token and amount
    • Remove spam transactions
  8. account_transactions: Get wallet transactions

    • List wallet transactions
    • Paginate through transaction history
    • Configurable result limits
  9. transaction_detail: Get transaction information

    • Detailed transaction data
    • Parsed instructions
    • Fee information
  10. transaction_actions: Get transaction actions

  • List token transfers
  • View program interactions
  • Decoded instruction data

Prerequisites

  • Python 3.10+
  • Solscan Pro API key (obtain from Solscan APIs)
  • Docker if running the MCP server as a container (recommended)

Installation

Using uv (Recommended)

When using uv, no specific installation is needed. We use uvx to directly run solscan-mcp-server.

Using pip

Alternatively, install via pip:

pip install solscan-mcp-server

Configuration

You can configure the server using either environment variables or command-line arguments:

OptionEnv VariableCLI ArgumentDefaultDescription
API KeySOLSCAN_API_KEY--api-keyRequiredYour Solscan Pro API key
TransportTRANSPORT--transportsseTransport protocol (sse or stdio)
HostHOST--host127.0.0.1Host to bind to when using SSE transport
PortPORT--port8050Port to listen on when using SSE transport
Log LevelLOG_LEVEL--verboseINFOLogging level (use -v or -vv for detail)

Running the Server

Using uvx (Recommended)
# Using environment variables:
SOLSCAN_API_KEY=your-key uvx solscan-mcp-server

# Using CLI arguments:
uvx solscan-mcp-server --api-key your-key
Using pip Installation
# Using environment variables:
SOLSCAN_API_KEY=your-key python -m solscan_mcp_server

# Using CLI arguments:
python -m solscan_mcp_server --api-key your-key
Using Docker
# Build the image
docker build -t solscan-mcp-server .

# Run with environment variables
docker run -e SOLSCAN_API_KEY=your-key solscan-mcp-server

Integration with MCP Clients

Claude Desktop Configuration
Using uvx (Recommended)

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "solscan": {
      "command": "uvx",
      "args": ["solscan-mcp-server"]
    }
  }
}
Using pip Installation
{
  "mcpServers": {
    "solscan": {
      "command": "python",
      "args": ["-m", "solscan_mcp_server"]
    }
  }
}
Zed Configuration

Add to your Zed settings.json:

"context_servers": {
  "solscan": {
    "command": {
      "path": "uvx",
      "args": ["solscan-mcp-server"]
    }
  }
}

Development

Running Tests
# Install dev dependencies
uv pip install -e ".[dev]"

# Run tests
pytest
Code Quality
# Run type checker
pyright

# Run linter
ruff check .
Debugging

You can use the MCP inspector to debug the server:

npx @modelcontextprotocol/inspector uvx solscan-mcp-server

For development debugging:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Contributing

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

License

This project is licensed under the MIT License. See the LICENSE file for details.

Comments

Markdown supported

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.