kukapay rug check mcp

kukapay rug check mcp avatar

by kukapay

An MCP server that detects potential risks in Solana meme tokens.

What is kukapay rug check mcp

Rug-Check-MCP

An MCP server that detects potential risks in Solana meme tokens, helping AI agents avoid rug pulls and unsafe projects.

License Python Version smithery badge

Features

  • Token Analysis Tool: The analysis_token tool retrieves and processes Solana token data from the Solsniffer API.
  • Structured Output: Returns detailed token information including name, symbol, Snif score, market cap, price, supply, risks, and audit status.

Prerequisites

  • Python 3.10 or higher
  • A Solsniffer API key (sign up at Solsniffer to obtain one)

Installation

Installing via Smithery

To install Rug Check for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @kukapay/rug-check-mcp --client claude

Manual Installation

  1. Clone the Repository:

    git clone https://github.com/kukapay/rug-check-mcp.git
    cd rug-check-mcp
    
  2. Install Dependencies: Ensure you have pip installed, then run:

    pip install mcp[cli] requests python-dotenv
    
  3. Client Configuration:

    "mcpServers": { 
      "rug-check-mcp": { 
        "command": "python", 
        "args": ["path/to/rug-check-mcp/main.py"], 
        "env": { 
          "SOLSNIFFER_API_KEY": "your_solsniffer_api_key_here" 
        } 
      } 
    }
    

Tool: analysis_token

  • Description: Analyzes a Solana token based on its address.
  • Input: token_address (string) - The Solana token address to analyze.
  • Output: A dictionary containing:
    • token_address: Token address
    • token_name: Token name
    • token_symbol: Token symbol
    • snif_score: Solsniffer risk score (0-100)
    • market_cap: Market capitalization in USD
    • price: Token price in USD
    • supply_amount: Total supply of the token
    • risks: High, moderate, and low risk details with counts and descriptions
    • audit_risk: Audit status (mint/freeze disabled, LP burned, top 10 holders)

Example Output

For token address 9VxExA1iRPbuLLdSJ2rB3nyBxsyLReT4aqzZBMaBaY1p:

{
  'token_address': '9VxExA1iRPbuLLdSJ2rB3nyBxsyLReT4aqzZBMaBaY1p',
  'token_name': 'REVSHARE',
  'token_symbol': 'REVS',
  'snif_score': 55,
  'market_cap': 271893.9423965262,
  'price': 0.000280011574,
  'supply_amount': 971009656.8955618,
  'risks': {
    'high': {
      'count': 3,
      'details': {
        'Mintable risks found': True,
        'Freeze risks found': True,
        'A private wallet owns a significant share of the supply': False,
        'Tokens auto-freeze risks found': True,
        'Significant ownership by top 10 wallets': False,
        'Significant ownership by top 20 wallets': False,
        'Permanent control risks found': True,
        'Presence of token metadata': True,
        'High locked supply risks found': None,
        'Sufficient liquidity detected': None,
        'Very low liquidity': None
      }
    },
    'moderate': {
      'count': 3,
      'details': {
        'Token metadata are immutable': False,
        'Token operates without custom fees': False,
        'Token has recent user activity': True,
        'Unknown liquidity pools': False,
        'Low count of LP providers': True
      }
    },
    'low': {
      'count': 1,
      'details': {
        'Contract was not recently deployed': False
      }
    }
  },
  'audit_risk': {
    'mint_disabled': True,
    'freeze_disabled': True,
    'lp_burned': False,
    'top_10_holders_significant': False
  }
}

Prompt Examples

Below are examples of prompts you might use in an MCP-compatible client (e.g., Claude Desktop) and the expected responses after the analysis_token tool is invoked.

Prompt:

"Can you analyze the Solana token at address 9VxExA1iRPbuLLdSJ2rB3nyBxsyLReT4aqzZBMaBaY1p?"

Response:

I've analyzed the token at address 9VxExA1iRPbuLLdSJ2rB3nyBxsyLReT4aqzZBMaBaY1p. Here's the summary:

- Token Name: REVSHARE (Symbol: REVS)
- Snif Score: 55/100 (Moderate risk)
- Market Cap: $288,875.29
- Price: $0.000297
- Total Supply: 971,266,696.90 tokens
- Risks:
  - High (3 risks):
    - Mintable risks found: True
    - Freeze risks found: True
    - Permanent control risks found: True
    - (Other factors: False)
  - Moderate (1 risk):
    - Low count of LP providers: True
    - (Other factors: False)
  - Low (0 risks):
    - (All factors: False)
- Audit Status:
  - Mint Disabled: Yes
  - Freeze Disabled: Yes
  - LP Burned: No
  - Top 10 Holders Significant: No

This token has moderate risks due to potential control issues and liquidity concerns, but minting and freezing are disabled for added safety.     

Prompt:

"What’s the risk profile of the token So11111111111111111111111111111111111111112?"

Response:

Here's the risk profile for the token at address So11111111111111111111111111111111111111112:

- Token Name: Wrapped SOL (Symbol: SOL)
- Snif Score: 92/100 (Low risk)
- Market Cap: $82,345,678.90
- Price: $176.54
- Total Supply: 466,567,890.12 tokens
- Risks:
  - High (0 risks):
    - (All factors: False)
  - Moderate (0 risks):
    - (All factors: False)
  - Low (1 risk):
    - Minor liquidity concentration: True
    - (Other factors: False)
- Audit Status:
  - Mint Disabled: Yes
  - Freeze Disabled: Yes
  - LP Burned: Yes
  - Top 10 Holders Significant: No

Wrapped SOL is a low-risk token with strong audit protections and only a minor liquidity concern, typical for a well-established asset.     

Prompt:

"Tell me about the token 4k3Dyjzvzp8eMZWUXbBCjEvwSkkk59S5iCNLY3QrkX6R."

Response:

Here's the analysis for the token at address 4k3Dyjzvzp8eMZWUXbBCjEvwSkkk59S5iCNLY3QrkX6R:

- Token Name: Raydium (Symbol: RAY)
- Snif Score: 85/100 (Low risk)
- Market Cap: $1,234,567.89
- Price: $4.72
- Total Supply: 261,567,890.12 tokens
- Risks:
  - High (0 risks):
    - (All factors: False)
  - Moderate (1 risk):
    - Moderate holder concentration: True
    - (Other factors: False)
  - Low (0 risks):
    - (All factors: False)
- Audit Status:
  - Mint Disabled: Yes
  - Freeze Disabled: Yes
  - LP Burned: Yes
  - Top 10 Holders Significant: No

Raydium is a low-risk token with solid audit protections. The moderate holder concentration indicates some centralization, but it’s not a major issue.     

License

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

Leave a Comment

Frequently Asked Questions

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.

What are MCP Servers?

MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.

How do MCP Servers work?

MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.

Are MCP Servers secure?

Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.

Related MCP Servers

chrisdoc hevy mcp avatar

chrisdoc hevy mcp

mcp
sylphlab pdf reader mcp avatar

sylphlab pdf reader mcp

An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.

pdf-parsetypescriptnodejs
aashari mcp server atlassian bitbucket avatar

aashari mcp server atlassian bitbucket

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.

atlassianrepositorymcp
aashari mcp server atlassian confluence avatar

aashari mcp server atlassian confluence

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.

atlassianmcpconfluence
prisma prisma avatar

prisma prisma

Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB

cockroachdbgomcp
Zzzccs123 mcp sentry avatar

Zzzccs123 mcp sentry

mcp sentry for typescript sdk

mcptypescript
zhuzhoulin dify mcp server avatar

zhuzhoulin dify mcp server

mcp
zhongmingyuan mcp my mac avatar

zhongmingyuan mcp my mac

mcp
zhixiaoqiang desktop image manager mcp avatar

zhixiaoqiang desktop image manager mcp

MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)

mcp
zhixiaoqiang antd components mcp avatar

zhixiaoqiang antd components mcp

An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询

designantdapi

Submit Your MCP Server

Share your MCP server with the community

Submit Now