On-chain Solana token safety β screen for rugs/honeypots and execute MEV-protected swaps.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
A lightweight MCP server that reads a Solana token's mint directly from the chain to screen for the common rug & honeypot traps before your agent trades β active mint/freeze authority and dangerous Token-2022 extensions (permanent delegate, transfer hooks, non-transferable, pausable) β then, for tokens that pass, builds the buy as an unsigned Jupiter transaction carrying a small Jito tip for faster inclusion. You sign it; the server never holds keys.
No install, no API key. Point your agent at the remote endpoint:
Then ask one question before any buy:
SAFE β clear. CAUTION β read the risks. DANGER β don't buy. That's the whole loop.
Three real mainnet tokens, one scan_token call each (scanned 2026-06-17 β re-run to verify, live state changes):
| Token | Verdict | Why |
|---|---|---|
| BONK | SAFE Β· 100 | authority renounced, liquid, sellable β no red flags |
| USDC | CAUTION Β· 70 | issuer keeps an active mint and freeze authority β your balance can be frozen |
fresh pump token 24tFβ¦i9pump | DANGER Β· 20 | no sell route (honeypot), 100% held by one wallet, $0 liquidity |
The honeypot is the one that matters: you could buy it and never sell. RugCheck AI flags it before your
agent spends a cent β even though the token is too new to be indexed anywhere else. Even USDC comes back
CAUTION, not SAFE, because the issuer can still freeze your balance β the verdict tells you the truth, not
a marketing label.
Screening
scan_token β full safety report in one call: authority, Token-2022 traps, honeypot, liquidity & holder concentration β SAFE/CAUTION/DANGER + a 0β100 scoreis_safe β quick yes/no gate: one boolean before you tradeverify_token_safety β on-chain audit: mint/freeze authority + Token-2022 traps + live marketcheck_authorities β mint / freeze authority and extension detectionsimulate_sell β can the token actually be sold? (honeypot check)simulate_trade β full round-trip (buy then sell back): real entry/exit cost & round-trip loss %check_liquidity β DEX liquidity, 24h volume, age, buys/sellsholders_breakdown β top-holder concentration (dump risk)token_age β freshness + real trading activityrug_forecast β heuristic rug ETA: probability + urgency window + factorsscammer_dna β intent score (0β100): how much the token's structure looks like a deliberate scamcheck_deployer β the wallets that hold power over the tokencompare_tokens β rank a basket of tokens safest-firstbatch_scan β scan up to 10 tokens at once, one report eachExecution
execute_safe_swap β re-screens the mint, then builds a Jito-tipped Jupiter swap (unsigned); refuses tokens that scan DANGERRemote (Streamable HTTP) β no install, point your agent at:
Listed on the official MCP Registry as
io.github.MrWizardlyLoaf/rugcheck-ai.
Self-host:
Cline / Claude Dev (VS Code) β in cline_mcp_settings.json:
Claude Desktop β in claude_desktop_config.json:
Cursor β Settings β MCP β Add β Streamable HTTP, then paste the endpoint URL.
Any MCP client β it's a standard Streamable HTTP MCP server; point your client at the /mcp endpoint and the 15 tools appear.
Most agents trade Solana tokens blind. RugCheck AI calls getAccountInfo on the mint and reads the
authorities and Token-2022 extensions itself, so you get a real verdict on a fresh launch instead of
unknown β and a live mint or freeze authority is flagged before you buy, not after.
Your agent needs to answer, before it spends a cent:
Built for AI trading agents, snipers and bots that buy SPL / Token-2022 tokens and need a fast on-chain rug check before entering β then a screened Jupiter route once a token clears.
How do I check if a Solana token is safe to buy?
Call scan_token(mint) β one call returns a SAFE / CAUTION / DANGER verdict covering mint/freeze
authority, Token-2022 traps, honeypot (sellability), liquidity and holder concentration, plus a
0β100 safety score.
How do I detect a honeypot before buying?
simulate_sell(mint) checks whether a live sell route exists β a token with no route is effectively
a honeypot even when nothing on-chain formally blocks selling.
How do I check holder concentration / whale dump risk?
holders_breakdown(mint) reports the largest wallets and what share of supply they control β high
concentration means one holder can crash the price on you.
How do I know if a token is a rug pull?
rug_forecast(mint) gives a heuristic rug probability and urgency window from real signals
(authority, Token-2022 traps, concentration, sell pressure, age). check_authorities and
check_deployer show exactly who holds power over the token.
Does it work on fresh / newly launched tokens?
Yes β it reads the mint directly on-chain (getAccountInfo), so you get a real verdict on a token
too new to be indexed elsewhere. token_age shows freshness and real trading activity.
Does it touch my wallet or sign anything?
No. Screening is read-only; execute_safe_swap only builds an UNSIGNED transaction for you to sign β
the server never holds keys, never signs, never sends.
Is it free? Do I need an API key? Remote server, no install, no API key. Point your agent at the endpoint and call the tools.
v1.2.0 β working, actively developed, CI-tested. Open source, auditable β the screening tools are
read-only (getAccountInfo); execute_safe_swap only builds an unsigned transaction for you to sign.
MIT licensed. Self-hostable. Built for Solana trading agents.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/rugcheck-ai)<a href="https://allmcps.com/mcp/rugcheck-ai"><img src="https://allmcps.com/api/badge/rugcheck-ai?style=directory" alt="Rugcheck Ai on AllMCPs" /></a>