{
  "markdown": "# onchain-safety-mcp\n\nMCP (Model Context Protocol) server that gives any AI agent **on-chain token-safety tools**\nfor **PulseChain, Monad, Base, and BSC** — including **PulseChain, which the major token-safety\nAPIs (GoPlus, Honeypot.is) don't support at all** (verified June 2026). If your agent touches\nPulseChain, this is the safety check.\n\nIt is a thin stdio client over the hosted API at [onchain.wick.pics](https://onchain.wick.pics)\n(engine `wick-safe/0.3`). Every check is **deterministic on-chain analysis — no LLM in the\nverdict path**, so results are fast, cheap, and reproducible: contract-risk heuristics,\nliquidity depth, honeypot transfer-simulation, LP-burn, ownership/renounce + privilege\ndetection, upgradeable-proxy detection, and a wallet approval (drainer) scanner. The free tier\nneeds no key. *Informational, not financial advice.*\n\n## Tools\n\n| tool | what it answers |\n|---|---|\n| `check_token_safety({ chain, address })` | Is this token a scam? Verdict (`SAFE` … `LIKELY_RUG`), 0–100 score, evidence checks. |\n| `fresh_rug_radar()` | What just launched, and is it safe? Last 20 freshly-created pools, safety-scored at creation. |\n| `exit_safety({ chain, token, sizeUsd, maxSlippage? })` | Could I sell $X of this at acceptable slippage? Size-aware price impact + safety verdict. |\n| `check_ownership({ chain, address })` | Is ownership renounced / upgradeable, and what can an active owner still do (mint, blacklist, pause, tax)? |\n| `safe_to_interact({ chain, address })` | One call → SAFE_TO_INTERACT / CAUTION / DO_NOT_INTERACT, bundling safety + ownership, with reasons. |\n| `wallet_approvals({ chain, owner })` | A wallet's active ERC-20 approvals, flagging unlimited grants — the drainer vector. |\n| `wallet_poison_check({ chain, owner })` | Address-poisoning scan: dust/look-alike transfers in a wallet's history that mimic a real counterparty to trick a paste-and-send of the wrong address. |\n\n`chain`: `pulsechain` | `monad` | `base` | `bsc` · token/address: `0x…` contract address.\nAgents should call `check_token_safety` / `exit_safety` before interacting with, buying, or\naccepting an unknown token.\n\n## Install (any MCP client — Claude Desktop, agent frameworks)\n\n```json\n{\n  \"mcpServers\": {\n    \"onchain-safety\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"github:aitools420/onchain-safety-mcp\"],\n      \"env\": { \"ONCHAIN_API_KEY\": \"wsk_…\" }\n    }\n  }\n}\n```\n\n`ONCHAIN_API_KEY` is **optional** — omit it for the free rate-limited tier. A `wsk_` key\nunlocks the paid deep tier (get one at [onchain.wick.pics](https://onchain.wick.pics)).\n\n## Pay-per-call for autonomous agents (x402)\n\nThe same engine is available with **no signup and no key** via the\n[x402](https://www.x402.org/) pay-per-call protocol — agents pay USDC on Base per request.\nMachine-readable index of every paid route (token-safety, fresh-rug radar, exit-safety):\n\n```\nhttps://onchain.wick.pics/.well-known/x402.json\n```\n\nHuman docs: [onchain.wick.pics/agents](https://onchain.wick.pics/agents)\n\n## Env\n\n| var | default | purpose |\n|---|---|---|\n| `ONCHAIN_API_BASE` | `https://onchain.wick.pics` | API host |\n| `ONCHAIN_API_KEY` | _(none — free tier)_ | `wsk_` key for the paid deep tier |\n\n## License\n\nMIT\n",
  "bytes": 3214,
  "sha": "ddb1f37c423497338ef4abac7b2a957a0f96f8286b8d94dc0bc9eab47cb5b230",
  "repo_slug": "aitools420/onchain-safety-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_aitools420_onchain_safety_mcp_6bc44d46/readme"
}