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:

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).

Related MCP server: onchain-safety-mcp

Example

"Is 0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed on 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