Bellchain
Crypto alert chains in your AI assistant: check alerts, test ideas with the replay, build chains.
作者提供的说明(英文原文)
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://web-production-58d585.up.railway.app/mcp在终端中运行这条命令
claude mcp add --transport http rugcheck-ai https://web-production-58d585.up.railway.app/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"rugcheck-ai": {
"url": "https://web-production-58d585.up.railway.app/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"rugcheck-ai": {
"type": "http",
"url": "https://web-production-58d585.up.railway.app/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://web-production-58d585.up.railway.app/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 MrWizardlyLoaf 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.2.0)于5个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Bellchain, Quidli Connect, Diamond Bitcoin Intelligence
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Crypto alert chains in your AI assistant: check alerts, test ideas with the replay, build chains.
Resolve social handles to wallets, score onchain reputation, pay in any ERC-20, SPL or native.
Bitcoin MCP: fee budgets, retained-block inclusion proofs and risk checks. Free service discovery.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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 — active mint/freeze authority and dangerous Token-2022 extensions (permanent delegate, transfer hooks, non-transferable, pausable) — 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:
https://web-production-58d585.up.railway.app/mcp
Then ask one question before any buy:
scan_token("DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263") # BONK
→ { verdict: "SAFE", safety_score: 100, sellable: true, risks: ["no red flags found"] }
SAFE → clear. CAUTION → read the risks. DANGER → don't buy. That's the whole loop.
Three real mainnet tokens, one scan_token call each (scanned 2026-06-17 — re-run to verify, live state changes):
| Token | Verdict | Why |
|---|---|---|
| BONK | SAFE · 100 | authority renounced, liquid, sellable — no red flags |
| USDC | CAUTION · 70 | issuer keeps an active mint and freeze authority — your balance *can* be frozen |
fresh pump token 24tF…i9pump | DANGER · 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 — 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 — the verdict tells you the truth, not a marketing label.
Screening
scan_token — full safety report in one call: authority, Token-2022 traps, honeypot, liquidity & holder concentration → SAFE/CAUTION/DANGER + a 0–100 scoreis_safe — quick yes/no gate: one boolean before you tradeverify_token_safety — on-chain audit: mint/freeze authority + Token-2022 traps + live marketcheck_authorities — mint / freeze authority and extension detectionsimulate_sell — can the token actually be sold? (honeypot check)simulate_trade — full round-trip (buy then sell back): real entry/exit cost & round-trip loss %check_liquidity — DEX liquidity, 24h volume, age, buys/sellsholders_breakdown — top-holder concentration (dump risk)token_age — freshness + real trading activityrug_forecast — heuristic rug ETA: probability + urgency window + factorsscammer_dna — intent score (0–100): how much the token's structure looks like a deliberate scamcheck_deployer — the wallets that hold power over the tokencompare_tokens — rank a basket of tokens safest-firstbatch_scan — scan up to 10 tokens at once, one report eachExecution
execute_safe_swap — re-screens the mint, then builds a Jito-tipped Jupiter swap (unsigned); refuses tokens that scan DANGERRemote (Streamable HTTP) — no install, point your agent at:
https://web-production-58d585.up.railway.app/mcp
Listed on the official MCP Registry as io.github.MrWizardlyLoaf/rugcheck-ai.
Self-host:
pip install -r requirements.txt
SOLANA_RPC= python server.py
Cline / Claude Dev (VS Code) — in cline_mcp_settings.json:
{ "mcpServers": { "rugcheck-ai": { "url": "https://web-production-58d585.up.railway.app/mcp" } } }
Claude Desktop — in claude_desktop_config.json:
{ "mcpServers": { "rugcheck-ai": { "command": "npx", "args": ["-y", "mcp-remote", "https://web-production-58d585.up.railway.app/mcp"] } } }
Cursor — Settings → MCP → Add → Streamable HTTP, then paste the endpoint URL.
Any MCP client — 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 — 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 — 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) — one call returns a SAFE / CAUTION / DANGER verdict covering mint/freeze authority, Token-2022 traps, honeypot (sellability), liquidity and holder concentration, plus a 0–100 safety score.
How do I detect a honeypot before buying? simulate_sell(mint) checks whether a live sell route exists — 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 — 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 — 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 — 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 — working, actively developed, CI-tested. Open source, auditable — 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.*