Rug Munch Mcp

io.github.amarodeabreuPublished by GitHub account amarodeabreuv1.0.1Updated Oct 27, 2026

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

VerifiedSTDIODesktop onlyFinanceSecurity & Monitoring

Overview

AI-generated overview

Crypto risk intelligence MCP server that lets an assistant score tokens for rug pulls, honeypots, deployer history and holder concentration before trading.

What you can do
  • Score tokens for rug-pull and honeypot risk, including a premium breakdown and batch checks of up to 20 tokens
  • Profile tokens and holders: price, liquidity, top-holder concentration, sniper and coordinated-buy detection
  • Investigate deployers and wallets: deployer history, serial ruggers, scammer wallets and community blacklist checks
  • Gather social signals: social OSINT, KOL shill detection and a global market risk index
  • Run AI forensic verdicts and analysis threads, and set 7-day webhook monitoring for risk changes
  • Check service health and accuracy metrics
When to use it
Useful when an assistant or trading agent needs a quick risk verdict on a token mint, deployer or wallet before transacting, or when screening batches of new tokens and their social signals.
Requirements
Runs as a local Python package installed with pip, or as a hosted remote endpoint. Talks to the provider's API; the base URL can be overridden with RUG_MUNCH_API_BASE. An optional RUG_MUNCH_API_KEY raises rate limits; without it the free tier is limited and paid calls use x402 USDC micropayments on Base or Solana.
Before you install
Most tools beyond the free daily check are paid per call, up to $2.00, via x402 USDC payments that spend real funds. An API key is requested by email and sent in the X-API-Key header. Token addresses and queries are sent to the provider's servers. Risk scores are third-party estimates, not guarantees.

Installation

In SourceWeft

  1. Open Rug Munch Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

🛡️ Marcus Rug Intel — MCP Server

[MCP] [PyPI] [Tools] [x402] [Free Tier] [Smithery] [Glama] [Coinbase x402 Ecosystem]

73% of new crypto tokens are scams or honeypots. This MCP server lets your AI agent check any token before transacting — the cheapest insurance in crypto.

19 tools for rug pull detection, honeypot scoring, deployer tracking, holder deep-dive, KOL shill detection, social OSINT, and LLM forensic analysis (Claude Sonnet 4 / Opus 4).

⚡ Try It Right Now (Free)

No install needed. 1 free call/day, no auth:

bash
curl -X POST https://cryptorugmunch.app/api/agent/v1/check-risk \  -H "Content-Type: application/json" \  -d '{"token_address": "7GCihgDB8fe6KNjn2MYtkzZcRjQy3t9GHdC8uHYmW2hr"}'

Response:

json
{  "token_address": "7GCihgDB8fe6KNjn2MYtkzZcRjQy3t9GHdC8uHYmW2hr",  "risk_score": 85,  "risk_level": "critical",  "recommendation": "AVOID",  "honeypot_risk": true,  "freeze_authority": true,  "token_name": "SuspiciousToken",  "token_symbol": "SCAM"}

🚀 Quick Start

Option 1: Install via pip

bash
pip install rug-munch-mcp

Option 2: Remote SSE (no install)

Connect directly to our hosted server:

https://cryptorugmunch.app/mcp/sse

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

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

Cursor / Windsurf / VS Code

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

OpenClaw

bash
mcporter config add rug-munch --command "rug-munch-mcp"mcporter call rug-munch.check_token_risk token_address=<MINT>

🔧 All 19 Tools

ToolWhatPrice
check_token_riskQuick risk score (0-100) + recommendationFree (1/day) or $0.04
check_token_risk_premiumFull breakdown + deployer + social OSINT$0.10
check_batch_riskUp to 20 tokens at once$0.30
check_deployer_historyDeployer wallet analysis — serial rugger?$0.06
get_token_intelligenceComplete token profile (price, holders, LP)$0.06
get_holder_deepdiveTop holders, concentration, sniper detection$0.10
get_social_osintSocial media presence and red flags$0.06
get_kol_shillsKOL/influencer shill detection$0.06
get_coordinated_buysDetect coordinated buying patterns$0.04
check_blacklistCommunity blacklist check$0.02
check_scammer_walletKnown scammer wallet check$0.02
get_market_risk_indexGlobal market risk overview$0.02
get_serial_ruggersKnown serial rugger wallets$0.02
marcus_quickAI verdict — Claude Sonnet 4 quick analysis$0.15
marcus_forensicsAI forensics — full Claude Sonnet 4 investigation$0.50
marcus_ultraAI deep analysis — Claude Opus 4$2.00
marcus_threadAI analysis thread for X/Twitter$1.00
watch_token7-day webhook monitoring for risk changes$0.20
get_api_statusService health + accuracy metricsFree

💳 Authentication Options

Free Tier (recommended to start)

  • 10 calls/day on check_token_risk — no auth needed
  • Just send the request, we'll answer

API Key (1,000 calls/hr)

bash
# Get a key instantly (free, anonymous)curl -X POST https://cryptorugmunch.app/api/agent/v1/keys/request \  -H "Content-Type: application/json" \  -d '{"email": "[email protected]"}'
# Use it on ALL 19 endpointscurl -X POST https://cryptorugmunch.app/api/agent/v1/check-batch \  -H "Content-Type: application/json" \  -H "X-API-Key: mri_your_key_here" \  -d '{"tokens": ["token1", "token2", "token3"]}'

x402 USDC Micropayments

Pay per-call with USDC on Base or Solana. See x402 docs.

Compatible with x402-fetch, x402-axios, Coinbase AgentKit, and any x402-enabled client.

🌐 Where We're Listed

RegistryLink
Official MCP Registryio.github.amarodeabreu/rug-munch-mcp
PyPIpip install rug-munch-mcp
Smitheryrug-munch-intelligence
Glamarug-munch-intelligence
x402 Bazaarcryptorugmunch.app
A2A Agent Card/.well-known/agent.json
awesome-x402PR #28 merged

📡 Discovery Endpoints (Free)

bash
# Service status & accuracy metricscurl https://cryptorugmunch.app/api/agent/v1/status
# OpenAPI speccurl https://cryptorugmunch.app/api/agent/v1/openapi.json
# Human-readable skill descriptioncurl https://cryptorugmunch.app/api/agent/v1/skill.md
# x402 payment detailscurl https://cryptorugmunch.app/.well-known/x402
# A2A agent cardcurl https://cryptorugmunch.app/.well-known/agent.json
# MCP server infocurl https://cryptorugmunch.app/.well-known/mcp.json

🤖 For Agent Developers

Reference Trading Agent

Full Python example agent that uses x402 to check tokens before trading: → CryptoRugMunch/x402-trading-agent

Coinbase AgentKit Plugin

Drop-in plugin for AgentKit-powered agents: → CryptoRugMunch/rug-agent-kit

🏗️ Architecture

Your Agent    │    ├── pip install rug-munch-mcp  (local STDIO)    │   └── Talks to cryptorugmunch.app API    │    ├── SSE: cryptorugmunch.app/mcp/sse  (remote, no install)    │    └── Direct HTTP: cryptorugmunch.app/api/agent/v1/*        ├── Free tier (1/day, no auth)        ├── API key (1000/hr, X-API-Key header)        └── x402 USDC (Payment-Signature header)

📊 Trust & Transparency

  • Trust score: Published at /api/agent/v1/status
  • Detection accuracy: 91%+ on known rug pulls
  • Uptime: 99.9%+ (monitored)
  • Response time: <500ms for cached, <5s for fresh scans
  • Feedback loop: POST /api/agent/v1/feedback — report false positives

License

MIT


⚠️ Note: This project was formerly known as CryptoRugMunch. The $CRM token is not affiliated with Marcus Rug Intel. We operate on a Stars-based subscription model — no token required.

Built by Marcus Rug Intel — the cheapest insurance in crypto.

Source: README.md at commit 364ca2f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts