Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

token-intel

REMOTE · NEXUS-ZERO.XYZ · SCANNED AUG 23

Pay-per-call Solana token risk intelligence: 8 tools via x402. From $0.005 USDC, no API key.

Available components

−53 this week 0 Trust /100

Dead

Every channel of this server has been unreachable for long enough to be marked dead. Its trust score is pinned to 0 and does not recover automatically: even once the server responds again it stays dead until it is manually reinstated.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security14
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools.Unverified
Tool Safety

Not scored yet: our latest scan of this component recorded no findings here. It fills in the next time we score it.

Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 4 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

Install

How do I install the token-intel MCP server?

token-intel is a hosted endpoint at https://nexus-zero.xyz/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · nexus-zero.xyz

# add to Claude Code
claude mcp add --transport http mikehunt69702-token-intel 'https://nexus-zero.xyz/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "mikehunt69702-token-intel": {
      "url": "https://nexus-zero.xyz/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "mikehunt69702-token-intel": {
      "type": "http",
      "url": "https://nexus-zero.xyz/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.mikehunt69702-token-intel]
url = "https://nexus-zero.xyz/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mikehunt69702-token-intel": {
      "type": "remote",
      "url": "https://nexus-zero.xyz/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add mikehunt69702-token-intel --url 'https://nexus-zero.xyz/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  mikehunt69702-token-intel:
    url: "https://nexus-zero.xyz/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "mikehunt69702-token-intel": {
      "Transport": "http",
      "Url": "https://nexus-zero.xyz/mcp"
    }
  }
}
# add to Vellum
assistant mcp add mikehunt69702-token-intel -t streamable-http -u 'https://nexus-zero.xyz/mcp'
// mcp.json
{
  "mcpServers": {
    "mikehunt69702-token-intel": {
      "type": "http",
      "url": "https://nexus-zero.xyz/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 23 Aug 26 −13

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 19 Aug 26 −13

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 18 Aug 26 −14

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 17 Aug 26 −13

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 16 Aug 26 −13

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 23 Aug 2026 · Probed https://nexus-zero.xyz/mcp

TLS unreached
DNSSEC secure

Validation of nexus-zero.xyz. Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
xyz. present 3599, 18130 8, 8 Verified
nexus-zero.xyz. present 59110 13 Verified
nexus-zero.xyz. Verified address RRset verified with the apex keys
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://nexus-zero.xyz/mcp Unreachable
http (plaintext) http://nexus-zero.xyz/mcp HTTPS enforced
MCP tools · 8 exposed · ~772 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_authorities ~78

Token authority audit for $0.005 USDC: mint / freeze / close / balance-mutable authorities, transfer hooks, metadata mutability, Token-2022 extension risks, and malicious-creator checks. Answers "can the dev structurally rug this?"

NameTypeReqDescription
mintstringyesBase58 Solana SPL token mint address to analyze

No output schema declared.

No examples provided.

check_safety ~97

FAST pre-trade safety gate for $0.005 USDC. Returns verdict, 0-100 risk score, confidence, a boolean safeToTrade, and kill-flags (rugged, nonTransferable/honeypot, maliciousTransferHook, maliciousCreator, mint & freeze authority). Built to be called on every candidate token before buying.

NameTypeReqDescription
mintstringyesBase58 Solana SPL token mint address to analyze

No output schema declared.

No examples provided.

check_tokens ~79

Batch rug-screen up to 20 Solana mints for $0.05 USDC flat. Returns verdict, 0-100 risk score, and safeToTrade for each mint. For watchlist / portfolio / multi-candidate scans in one paid call.

NameTypeReqDescription
mintsarrayyes1-20 base58 Solana mint addresses

No output schema declared.

No examples provided.

get_holder_analysis ~68

Holder concentration & insider signals for $0.01 USDC: top-10 holder % and locked %, top-5 %, holder count, and insider-wallet detection. Flags dev/insider control of supply.

NameTypeReqDescription
mintstringyesBase58 Solana SPL token mint address to analyze

No output schema declared.

No examples provided.

get_lp_analysis ~80

LP-lock depth for $0.01 USDC: per-pool TVL, LP-locked %, LP-burn % (burned LP is locked forever), and top LP holders with lock detail. Answers "is liquidity actually locked, or just claimed to be?"

NameTypeReqDescription
mintstringyesBase58 Solana SPL token mint address to analyze

No output schema declared.

No examples provided.

get_new_tokens ~154

Fresh Solana tokens from the recent window, PRE-SCORED with token-intel rug risk. The sniper feed: discovery + safety fused, so you find new launches that are already rug-checked. Optional filters: minutes (lookback), minLiquidityUsd, maxRisk (0-100), safeOnly, limit. (Server-side feed must be enabled.)

NameTypeReqDescription
limitintegermax results (default 50)
maxRisknumbermaximum composite risk score (0-100)
minLiquidityUsdnumberminimum USD liquidity
minutesintegeronly tokens discovered in the last N minutes
safeOnlybooleanonly tokens where safeToTrade is true

No output schema declared.

No examples provided.

get_token_intel ~121

Full Solana token rug-risk intelligence for $0.01 USDC (x402). Returns verdict CLEAN|LOW_RISK|MODERATE_RISK|HIGH_RISK|RUGGED, 0-100 risk score, confidence, LP-lock depth (pool TVL, locked %, burn %), top-10 holder concentration with lock status, mint/freeze/close authority flags, and per-source breakdown from RugCheck + GoPlus + on-chain data.

NameTypeReqDescription
mintstringyesBase58 Solana SPL token mint address to analyze

No output schema declared.

No examples provided.

rank_token_candidates ~95

Rank up to 20 Solana token candidates for $0.05 USDC flat using the existing composite oracle. Deterministic safest-first ordering: available data, safeToTrade, lower risk score, higher confidence, more responding sources, then mint-address tie-break. Returns decisive reasons and kill flags; no opaque model score.

NameTypeReqDescription
mintsarrayyes1-20 base58 Solana mint addresses to rank

No output schema declared.

No examples provided.

Common questions

What is the token-intel MCP server?

token-intel is an MCP server listed in the public MCP registry as io.github.MikeHunt69702/token-intel. Pay-per-call Solana token risk intelligence: 8 tools via x402. From $0.005 USDC, no API key. This page covers its hosted endpoint (https://nexus-zero.xyz/mcp).

Is the token-intel MCP server safe to use?

token-intel scores 0 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the token-intel MCP server expose?

token-intel exposes 8 tools: get_token_intel, check_safety, get_lp_analysis, get_holder_analysis, check_authorities, and 3 more. Their descriptions and schemas cost roughly 772 tokens of context every time the server is loaded.

Does the token-intel MCP server require authentication?

Its publisher declares no required credentials for token-intel. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

Is the token-intel MCP server still maintained?

token-intel has been unreachable for long enough that we treat it as dead, and its score is pinned to zero. We last reached this channel on 27 July 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.