Skip to content

RugShield — Solana Token Safety Scanner

by zikriz · remote · no sign-in to list tools · v1.0.0 · published by GitHub user zikriz

Solana token rug-pull detection for AI trading agents. Score, authorities, liquidity.

Changes · 7
CompareRegistry entry

7 tools: 7 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http rugshield https://165-227-136-26.sslip.io/shield/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

7 tools

Changes things 7Claude Code: ask
  • add_creditsOWNER ONLY: add credits to a customer's key after payment is received.No findings

    Why it is in this group

    • The name "add_credits" says "add": a word for a change.
    Description, as the server wrote it
    OWNER ONLY: add credits to a customer's key after payment is received.

    Annotations the server declares

    • title: Add Credits (Owner Only)
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • admin_statsOWNER ONLY: business overview — customers, calls, credits, plans.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    OWNER ONLY: business overview — customers, calls, credits, plans.

    Annotations the server declares

    • title: Admin Stats (Owner Only)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • check_creditsCheck remaining credits for an API key.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check remaining credits for an API key.

    Annotations the server declares

    • title: Check Credit Balance
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • register_free_keyRegister a free API key with starter credits.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
    Register a free API key with starter credits. One per agent; paid top-ups available from the operator.

    Annotations the server declares

    • title: Register Free API Key
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • scan_tokenFull safety scan of one Solana token mint: rug-pull risk score (0-100), verdict, mint/freeze authority, holder concentration, liquidity, pair age.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Full safety scan of one Solana token mint: rug-pull risk score (0-100), verdict, mint/freeze authority, holder concentration, liquidity, pair age. Costs 1 credit. ALWAYS scan before buying a token.

    Annotations the server declares

    • title: Scan Token Safety
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • scan_tokensBulk scan up to 20 token mints.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Bulk scan up to 20 token mints. Costs 1 credit per token.

    Annotations the server declares

    • title: Scan Tokens (Bulk)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http rugshield https://165-227-136-26.sslip.io/shield/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__rugshield__register_free_key",
      "mcp__rugshield__scan_token",
      "mcp__rugshield__scan_tokens",
      "mcp__rugshield__trending_tokens",
      "mcp__rugshield__check_credits",
      "mcp__rugshield__admin_stats",
      "mcp__rugshield__add_credits"
    ],
    "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 rugshield. Review it before you use it.