The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Solrisk MCP listing page.
A hosted Model Context Protocol server that gives any AI assistant or agent an instant rug / honeypot / dump risk score (0–100) for any Solana SPL token, straight from on-chain signals — no API key, no install, one URL.
Built for Claude Code, Claude Desktop, Cursor, and any MCP-capable agent framework.
The solana_token_risk tool takes a token mint address and returns a JSON risk report:
0 (safe) … 100 (high rug/honeypot/dump risk)Claude Code
Claude Desktop / Cursor / generic MCP client — add to your MCP config:
Then ask: "Check the rug risk of token <mint>."
The MCP tool above is free. For programmatic pay-per-call at scale, the same engine is exposed as a pay-per-use HTTP API via x402 (USDC on Solana, $0.01/call, no account):
It returns an HTTP 402 with an x402 payment challenge; pay and retry to get the full report.
Discovery: /.well-known/x402 ·
/openapi.json ·
/llms.txt
MIT