Token Safety (Base)
by token-safety-mcp.restockalarm.workers.dev · remote · no sign-in to list tools · v1.1.0 · published by dev.workers.restockalarm.token-safety-mcp
Base token safety: one-call verdict, risk score, rug check, holders, momentum. x402 + free demo.
6 tools: 6 change things.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things6Claude Code: ask: see these tools
- Only reads0Claude Code: allow
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http token-safety https://token-safety-mcp.restockalarm.workers.dev/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
6 tools
Changes things 6Claude Code: ask
holder_checkHolder analysis for an ERC-20 on Base: top 10 holders typed wallet/contract/LP/burn, wallet concentration, distribution and bundling check.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Holder analysis for an ERC-20 on Base: top 10 holders typed wallet/contract/LP/burn, wallet concentration, distribution and bundling check. Use to judge supply concentration. $0.02 via x402.
momentum_scoreMomentum score 0-100 for an ERC-20 on Base from 24 h volume, volume vs liquidity and price change, with confidence low/medium/high.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Momentum score 0-100 for an ERC-20 on Base from 24 h volume, volume vs liquidity and price change, with confidence low/medium/high. Null for stablecoins. Use to rank Base tokens by activity. $0.02 via x402.
rug_checkRug-pull check for an ERC-20 on Base: rug_pull true/false, confidence and 5 signals (liquidity removal, wash trading, LP lock, owner wallet, honeypot/tax).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Rug-pull check for an ERC-20 on Base: rug_pull true/false, confidence and 5 signals (liquidity removal, wash trading, LP lock, owner wallet, honeypot/tax). Use before buying a new Base token. $0.02 via x402.
token_riskRisk score 0-100 (higher = riskier) for an ERC-20 on Base: liquidity, top-5 holder concentration, honeypot/tax flags.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Risk score 0-100 (higher = riskier) for an ERC-20 on Base: liquidity, top-5 holder concentration, honeypot/tax flags. Use before buying or listing an unknown Base token. $0.02 via x402. Not investment advice.
token_safety_demoFree demo (5 calls/day per IP): run one of token_verdict, token_risk, rug_check, holder_check, momentum_score without payment.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Free demo (5 calls/day per IP): run one of token_verdict, token_risk, rug_check, holder_check, momentum_score without payment. Same output as the paid tool.
token_verdictOne-call verdict for an ERC-20 on Base: runs token risk, rug-pull, holder and momentum checks plus contract flags (proxy, blacklist, pause, selfdestruct) and returns avoid / high_r…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it One-call verdict for an ERC-20 on Base: runs token risk, rug-pull, holder and momentum checks plus contract flags (proxy, blacklist, pause, selfdestruct) and returns avoid / high_risk / caution / low_risk with a one-line English summary. Use once before buying or listing an unknown Base token. $0.05 via x402. Not investment advice.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http token-safety https://token-safety-mcp.restockalarm.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__token-safety__token_verdict",
"mcp__token-safety__token_risk",
"mcp__token-safety__rug_check",
"mcp__token-safety__holder_check",
"mcp__token-safety__momentum_score",
"mcp__token-safety__token_safety_demo"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as token-safety. Review it before you use it.