Onchain Safety MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 60 installs a week from npm. Last commit 4 Jul 2026.
Token-safety for AI agents: rug/honeypot verdict + score across PulseChain, Monad, Base & BSC
Today is the operative word: we check Onchain Safety MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add onchain-safety-mcp -- npx -y @wickpics/onchain-safety-mcp
{
"mcpServers": {
"onchain-safety-mcp": {
"args": [
"-y",
"@wickpics/onchain-safety-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.onchain-safety-mcp]
command = "npx"
args = ["-y", "@wickpics/onchain-safety-mcp"]
{
"mcpServers": {
"onchain-safety-mcp": {
"args": [
"-y",
"@wickpics/onchain-safety-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"onchain-safety-mcp": {
"args": [
"-y",
"@wickpics/onchain-safety-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ONCHAIN_API_KEY (Optional wsk_ key for the paid deep tier (omit for the free rate-limited tier).).
The author declared them in the registry entry; get the values from the project itself.
Pre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402.
RiskDataApi — Solana token risk scoring for AI agents. Safety score, insider clusters, honeypot.
Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.
Merchant trust verification for AI agents. One call = trust score, badge, and purchase safety.
Pre-trade safety check for AI agents: honeypot, tax, liquidity and rug risk before you buy.
Cross-chain DEX for AI agents. Swap tokens across 7+ chains.
23 Solana on-chain data tools for AI agents via x402 micropayments + rug-screen token verdict
Token safety oracle (Base & BSC): honeypot/tax sim, contract powers, A-F risk grade.
Answers built from our own checks of this server.