Rug Munch Intelligence
# š”ļø Marcus Rug Intel ā MCP Server
<!-- mcp-name: io.github.amarodeabreu/rug-munch-mcp -->
[](https://modelcontextprotocol.io)
[](https://pypi.org/project/rug-munch-mcp/)
[](https://cryptorugmunch.app/api/agent/v1/status)
[](https://cryptorugmunch.app/.well-known/x402)
[](https://cryptorugmunch.app/api/agent/v1/check-risk)
[](https://smithery.ai/server/@CryptoRugMunch/rug-munch-intelligence)
[](https://glama.ai/mcp/servers/@CryptoRugMunch/rug-munch-intelligence)
[](https://github.com/coinbase/x402/blob/main/services/rug-munch-intelligence/metadata.json)
> **73% of new crypto tokens are scams or honeypots.** This MCP server lets your AI agent check any token before transacting ā 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).
## ā” 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"
}
```
## š 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>
```
## š§ All 19 Tools
| Tool | What | Price |
|------|------|-------|
| `check_token_risk` | Quick risk score (0-100) + recommendation | **Free** (1/day) or $0.04 |
| `check_token_risk_premium` | Full breakdown + deployer + social OSINT | $0.10 |
| `check_batch_risk` | Up to 20 tokens at once | $0.30 |
| `check_deployer_history` | Deployer wallet analysis ā serial rugger? | $0.06 |
| `get_token_intelligence` | Complete token profile (price, holders, LP) | $0.06 |
| `get_holder_deepdive` | Top holders, concentration, sniper detection | $0.10 |
| `get_social_osint` | Social media presence and red flags | $0.06 |
| `get_kol_shills` | KOL/influencer shill detection | $0.06 |
| `get_coordinated_buys` | Detect coordinated buying patterns | $0.04 |
| `check_blacklist` | Community blacklist check | $0.02 |
| `check_scammer_wallet` | Known scammer wallet check | $0.02 |
| `get_market_risk_index` | Global market risk overview | $0.02 |
| `get_serial_ruggers` | Known serial rugger wallets | $0.02 |
| `marcus_quick` | AI verdict ā Claude Sonnet 4 quick analysis | $0.15 |
| `marcus_forensics` | AI forensics ā full Claude Sonnet 4 investigation | $0.50 |
| `marcus_ultra` | AI deep analysis ā Claude Opus 4 | $2.00 |
| `marcus_thread` | AI analysis thread for X/Twitter | $1.00 |
| `watch_token` | 7-day webhook monitoring for risk changes | $0.20 |
| `get_api_status` | Service health + accuracy metrics | Free |
## š³ Authentication Options
### Free Tier (recommended to start)
- **10 calls/day** on `check_token_risk` ā 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": "you@example.com"}'
# Use it on ALL 19 endpoints
curl -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](https://cryptorugmunch.app/.well-known/x402).
Compatible with [x402-fetch](https://github.com/coinbase/x402), [x402-axios](https://github.com/coinbase/x402), [Coinbase AgentKit](https://github.com/CryptoRugMunch/rug-agent-kit), and any x402-enabled client.
## š Where We're Listed
| Registry | Link |
|----------|------|
| **Official MCP Registry** | `io.github.amarodeabreu/rug-munch-mcp` |
| **PyPI** | [`pip install rug-munch-mcp`](https://pypi.org/project/rug-munch-mcp/) |
| **Smithery** | [rug-munch-intelligence](https://smithery.ai/server/@CryptoRugMunch/rug-munch-intelligence) |
| **Glama** | [rug-munch-intelligence](https://glama.ai/mcp/servers/@CryptoRugMunch/rug-munch-intelligence) |
| **x402 Bazaar** | [cryptorugmunch.app](https://api.cdp.coinbase.com/platform/v2/x402/discovery/resources?resource_server=cryptorugmunch.app) |
| **A2A Agent Card** | [`/.well-known/agent.json`](https://cryptorugmunch.app/.well-known/agent.json) |
| **awesome-x402** | [PR #28 merged](https://github.com/xpaysh/awesome-x402) |
## š” Discovery Endpoints (Free)
```bash
# Service status & accuracy metrics
curl https://cryptorugmunch.app/api/agent/v1/status
# OpenAPI spec
curl https://cryptorugmunch.app/api/agent/v1/openapi.json
# Human-readable skill description
curl https://cryptorugmunch.app/api/agent/v1/skill.md
# x402 payment details
curl https://cryptorugmunch.app/.well-known/x402
# A2A agent card
curl https://cryptorugmunch.app/.well-known/agent.json
# MCP server info
curl https://cryptorugmunch.app/.well-known/mcp.json
```
## š¤ For Agent Developers
### Reference Trading Agent
Full Python example agent that uses x402 to check tokens before trading:
ā [CryptoRugMunch/x402-trading-agent](https://github.com/CryptoRugMunch/x402-trading-agent)
### Coinbase AgentKit Plugin
Drop-in plugin for AgentKit-powered agents:
ā [CryptoRugMunch/rug-agent-kit](https://github.com/CryptoRugMunch/rug-agent-kit)
## šļø Architecture
```
Your Agent
ā
āāā pip install rug-munch-mcp (local STDIO)
ā āāā Talks to cryptorugmunch.app API
ā
āāā SSE: cryptorugmunch.app/mcp/sse (remote, no install)
ā
āāā Direct HTTP: cryptorugmunch.app/api/agent/v1/*
āāā Free tier (1/day, no auth)
āāā API key (1000/hr, X-API-Key header)
āāā x402 USDC (Payment-Signature header)
```
## š 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` ā report false positives
## License
MIT
---
> **ā ļø 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 ā no token required.
*Built by [Marcus Rug Intel](https://x.com/MarcusRugIntel) ā the cheapest insurance in crypto.*
TDQS
Scored across 19 tools
The tool set has clear thematic grouping (risk checks, intelligence gathering, AI forensics, monitoring), but there is significant overlap within categories. For example, check_token_risk, check_token_risk_premium, and the marcus_* tools all perform risk analysis with varying depth, which could confuse an agent about which to select for a given scenario. Descriptions help differentiate, but the boundaries are not always sharp.
Most tools follow a consistent verb_noun pattern (e.g., check_batch_risk, get_api_status, watch_token), with clear action prefixes like 'check', 'get', and 'marcus_'. The marcus_* tools deviate slightly by using a proper name prefix instead of a verb, but they maintain internal consistency. Overall, the naming is predictable and readable.
With 19 tools, the count is borderline high for a risk analysis server, leaning toward heavy. While the domain (crypto token security) is complex and may justify many tools, some tools feel redundant (e.g., multiple AI forensic options) or niche (e.g., marcus_thread), suggesting potential over-scoping that could overwhelm an agent.
The tool surface comprehensively covers the domain of crypto token risk assessment and intelligence. It includes core checks (token, deployer, wallet), advanced analysis (AI forensics, holder deep dives), market-wide metrics, social OSINT, and proactive monitoring. There are no obvious gaps; agents can perform end-to-end risk evaluation and monitoring workflows.