MCP.Market

Onchain Safety MCP server

by aitools420·io.github.aitools420/onchain-safety-mcp·v0.2.0
No reviews yet

Token-safety for AI agents: rug/honeypot verdict + score across PulseChain, Monad, Base & BSC

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars65 downloads/wk

Reviews

Write one

Nobody has reviewed Onchain Safety yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Onchain Safety tools (7)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_ownership

    Is ownership renounced, is the contract upgradeable (proxy), and what powers can an active owner still use (mint / blacklist / pause / adjust tax)? Deterministic on-chain read — call before trusting a token long-term.

  • check_token_safety

    Scam/safe verdict for an ERC-20 token on PulseChain, Monad, Base, or BSC. Returns verdict (SAFE / LOW_RISK / CAUTION / HIGH_RISK / LIKELY_RUG / NOT_A_TOKEN / UNKNOWN), a 0-100 score, confidence, and the evidence checks (contract risk, liquidity depth, honeypot transfer-sim, LP-burn). Call this before interacting with, buying, or accepting an unknown token. Informational only — an automated assessm

  • exit_safety

    Can you sell $X of a token at acceptable slippage? Size-aware price-impact check (on-chain reserves + routed quote) plus the safety verdict. Call this BEFORE buying a position you may need to exit, or before accepting a token as payment. Informational only — an automated assessment that can be wrong; not financial advice.

  • fresh_rug_radar

    The most recently created liquidity pools, each safety-scored the moment it appeared (verdict, 0-100 score, seconds-since-creation). New tokens are where the rugs are — call this to see what just launched and whether it is safe. Free tier returns the last 20 scored pools; a paid key unlocks the fuller real-time feed.

  • safe_to_interact

    One call before touching a contract: bundles the safety verdict + ownership/privileges into a single recommendation — SAFE_TO_INTERACT / CAUTION / DO_NOT_INTERACT — with reasons. The de-risked "should I touch this?" answer for an agent mid-execution.

  • wallet_approvals

    Enumerate a wallet's active ERC-20 approvals (allowances granted to spender contracts) and flag the unlimited ones — the classic wallet-drainer vector. Call to audit what could quietly drain a wallet. Scans a recent block window.

  • wallet_poison_check

    Scan a wallet's recent incoming transfers for address-poisoning attacks — dust/zero-value transfers from lookalike addresses (first-4+last-4 chars matching a real counterparty the wallet has paid) seeded to trick a copy-paste of the wrong address. Call before sending to a "recently used" address to avoid pasting a poisoned lookalike.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 85 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Onchain Safety compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 48,255 servers
Tools
7
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
65
more than 51% of 12,191 servers with a package

What its tools let an agent do: 7 read

Install Onchain Safety in Claude Code, Cursor or VS Code

Runs npx -y @wickpics/onchain-safety-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add onchain-safety-mcp -- npx -y @wickpics/onchain-safety-mcp
Add to Cursor

What the publisher says

From the Onchain Safety repository's README, as published. We do not edit it. Read it on GitHub

onchain-safety-mcp

MCP (Model Context Protocol) server that gives any AI agent on-chain token-safety tools for PulseChain, Monad, Base, and BSC — including PulseChain, which the major token-safety APIs (GoPlus, Honeypot.is) don't support at all (verified June 2026). If your agent touches PulseChain, this is the safety check.

It is a thin stdio client over the hosted API at onchain.wick.pics (engine wick-safe/0.3). Every check is deterministic on-chain analysis — no LLM in the verdict path, so results are fast, cheap, and reproducible: contract-risk heuristics, liquidity depth, honeypot transfer-simulation, LP-burn, ownership/renounce + privilege detection, upgradeable-proxy detection, and a wallet approval (drainer) scanner. The free tier needs no key. Informational, not financial advice.

Tools

chain: pulsechain | monad | base | bsc · token/address: 0x… contract address. Agents should call checktokensafety / exit_safety before interacting with, buying, or accepting an unknown token.

Install (any MCP client — Claude Desktop, agent frameworks)

{
  "mcpServers": {
    "onchain-safety": {
      "command": "npx",
      "args": ["-y", "github:aitools420/onchain-safety-mcp"],
      "env": { "ONCHAIN_API_KEY": "wsk_…" }
    }
  }
}

ONCHAINAPIKEY is optional — omit it for the free rate-limited tier. A wsk_ key unlocks the paid deep tier (get one at onchain.wick.pics).

Pay-per-call for autonomous agents (x402)

The same engine is available with no signup and no key via the x402 pay-per-call protocol — agents pay USDC on Base per request. Machine-readable index of every paid route (token-safety, fresh-rug radar, exit-safety):

https://onchain.wick.pics/.well-known/x402.json

Human docs: onchain.wick.pics/agents

Env

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Onchain Safety: common questions

Is Onchain Safety MCP server safe?
Mostly: it is graded B (78/100). Read the Onchain Safety safety report
How do I install Onchain Safety?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Onchain Safety need an API key?
Yes. The registry entry asks for ONCHAIN_API_KEY.
Is Onchain Safety maintained?
The last commit was 123 days ago (2026-07-03). The latest release is v0.2.0.
What can I use instead of Onchain Safety?
Servers from other publishers that do the same job: Labelhead Artist Momentum MCP server.
How does Onchain Safety compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); tools 7 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Onchain Safety

Same job from other publishers: the closest match first, then the best rated.