Rug MCP Server

Crypto risk intelligence: 19 tools for rug pull detection, AI forensics, and token analysis.

Remote serverstreamable-httpPython

What is the Rug MCP server?

If you already use Rug, the rug mcp server is the piece that lets your assistant work with it directly. Crypto risk intelligence: 19 tools for rug pull detection, AI forensics, and token analysis.

What the server does

Connect directly to our hosted server: https://cryptorugmunch.app/mcp/sse

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • check_token_risk — Quick risk score (0-100) + recommendation
  • check_token_risk_premium — Full breakdown + deployer + social OSINT
  • check_batch_risk — Up to 20 tokens at once
  • check_deployer_history — Deployer wallet analysis — serial rugger?
  • get_token_intelligence — Complete token profile (price, holders, LP)
  • get_holder_deepdive — Top holders, concentration, sniper detection
  • get_social_osint — Social media presence and red flags
  • get_kol_shills — KOL/influencer shill detection
  • get_coordinated_buys — Detect coordinated buying patterns
  • check_blacklist — Community blacklist check
  • check_scammer_wallet — Known scammer wallet check
  • get_market_risk_index — Global market risk overview

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Rug's toolset — check_token_risk, check_token_risk_premium, check_batch_risk and 11 more — is a fair guide to whether it matches your workflow. It is maintained by amarodeabreu; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Rug's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Rug.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
check_token_riskQuick risk score (0-100) + recommendation
check_token_risk_premiumFull breakdown + deployer + social OSINT
check_batch_riskUp to 20 tokens at once
check_deployer_historyDeployer wallet analysis — serial rugger?
get_token_intelligenceComplete token profile (price, holders, LP)
get_holder_deepdiveTop holders, concentration, sniper detection
get_social_osintSocial media presence and red flags
get_kol_shillsKOL/influencer shill detection
get_coordinated_buysDetect coordinated buying patterns
check_blacklistCommunity blacklist check
check_scammer_walletKnown scammer wallet check
get_market_risk_indexGlobal market risk overview
get_serial_ruggersKnown serial rugger wallets
marcus_quickAI verdict — Claude Sonnet 4 quick analysis

How to install the Rug MCP server

### Cursor / Windsurf / VS Code

```json
{
  "mcpServers": {
    "rug-munch": {
      "command": "rug-munch-mcp",
      "env": {}
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Rug to check token risk.
  • Use Rug to check token risk premium.
  • Use Rug to check batch risk.

Frequently asked questions

It connects Rug to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (check_token_risk, check_token_risk_premium, check_batch_risk, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Rug directly.