Skip to content

Solana Token Intelligence

by k0diak · remote · no sign-in to list tools · v2.0.0 · published by GitHub user k0diak

Solana token due-diligence: 3-source fused risk verdict incl. LP-lock depth. $0.01 via x402.

Changes · 2
CompareRegistry entry

2 tools: 2 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 token-intel https://token-intel.xrpbreadcrumbs.workers.dev/mcp

Tools

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

2 tools

Changes things 2Claude Code: ask
  • token_intelFused safety + market read on any Solana token: mint/freeze authorities, holder concentration, dev holdings, organic score, liquidity cross-checked across three independent sources…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
    Fused safety + market read on any Solana token: mint/freeze authorities, holder concentration, dev holdings, organic score, liquidity cross-checked across three independent sources (Jupiter, DexScreener, RugCheck incl. LP-lock depth), synthesized 0-100 risk verdict. PAID: $0.01 USDC on Base or Solana (x402 v2, keyless). To pay: fetch requirements by calling this tool once (returned in-band), settle via an x402 client, then retry with the base64 payment payload either as the '_payment' argument or the X-PAYMENT HTTP header. Try token_intel_demo first — it is free and proves the pipeline live.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • token_intel_demoFree.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
    Free. Returns the complete three-source intelligence report for a fixed sample token (BONK), exercising the exact production pipeline — verify output quality before paying for token_intel.

    Annotations the server declares

    • readOnlyHint: true
    • 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 2.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http token-intel https://token-intel.xrpbreadcrumbs.workers.dev/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__token-intel__token_intel",
      "mcp__token-intel__token_intel_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-intel. Review it before you use it.