ton-jetton-risk-mcp
MCP server that screens any TON jetton (token) for rug-pull and honeypot risk. Returns a live on-chain 0–100 risk score with flags: mint authority, holder concentration, DEX liquidity, taxable transfer, blacklist, and a honeypot heuristic.
README
token-risk MCP (ton-jetton-risk-mcp)
An MCP server that gives an AI agent tools to screen any token for rug-pull / honeypot risk — live, on-chain, free, no API keys.
Covers three ecosystems:
| tool | chains | what it checks |
|---|---|---|
assess_evm_token_risk |
Ethereum, BSC, Base, Arbitrum, Polygon, Optimism, Avalanche | honeypot (static + live buy/sell simulation on ETH/BSC/Base), buy/sell tax, owner powers (mint / pause / blacklist / balance change), hidden owner, proxy, open source, DEX liquidity, holder concentration |
assess_solana_token_risk |
Solana | mint / freeze authority, balance-mutable, closable accounts, transfer hooks & fees, DEX TVL + top pools, holder concentration; flags dataSparse for minutes-old mints |
assess_ton_jetton_risk |
TON | mint authority not revoked, admin present, holder concentration, DEX liquidity & blacklist (STON.fi), taxable transfer, honeypot heuristic |
Every tool returns a 0–100 risk score plus concrete flags and the raw facts (taxes, holders, liquidity, owner) as structured JSON.
Data sources: GoPlus token_security, honeypot.is v2 simulation, TonAPI, STON.fi — all live reads, nothing cached, nothing invented.
Install
No global install — run straight from GitHub with npx.
Claude Desktop / Claude Code (claude_desktop_config.json or .mcp.json):
{
"mcpServers": {
"token-risk": {
"command": "npx",
"args": ["-y", "github:mrvlyouknowwho/ton-jetton-risk-mcp"]
}
}
}
Works the same in any MCP client (Cursor, Windsurf, VS Code, …).
Optional env: TONAPI_KEY — a tonapi.io key raises TON rate limits (works fine without).
Example
"Is
0x4ed4E862860beD51a9570b96d89aF5E1B0Efefedon Base safe to buy?"
The agent calls assess_evm_token_risk and gets back score 0, a passing live
sell simulation, taxes 0/0, open-source contract, deep liquidity — with every
flag it would have raised if any of that were off.
Related
- HTTP pay-per-call version of the same analyzers (x402, USDC):
https://213-165-37-71.sslip.io/v1/evm/token/risk·/v1/jetton/risk— machine-readable schema at/openapi.json - Web checker (browser, free): https://mrvlyouknowwho.github.io/ruglens/
- Telegram: @RugLens_bot
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.