mcpbeat Sign in

Trust Check MCP Server

answering

Trust Check is answering right now. Last checked 10 min ago. It exposes 2 tools.

Crypto safety for agents on Base: token honeypot/tax test and safe-to-send address poisoning check.

Uptime history 15 days of history · worst day 99%
15 days agonow
100.0%
Uptime 24h
92 of 92 checks
2
Tools
read from the server
912 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Trust Check every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add trust-check --transport http https://trust-check.gm-tools.workers.dev/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "trust-check": {
      "url": "https://trust-check.gm-tools.workers.dev/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.trust-check]
url = "https://trust-check.gm-tools.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "trust-check": {
      "url": "https://trust-check.gm-tools.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "trust-check": {
      "url": "https://trust-check.gm-tools.workers.dev/mcp"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

address
check_address_safety
Before sending crypto on Base, check the destination: scam blacklists, address poisoning (a look-alike of an address you really use; pass `from` = your wallet), token contracts and burn addresses where funds are lost, never-used addresses. Returns a verdict with reasons. 5 free checks per day, then $0.002 per check via x402 (USDC on Base).
token
check_token_safety
Before buying a token on Base, check it: simulates a real buy and sell (honeypot and hidden-tax test), reads owner powers (mint, blacklist, fee changes, pause), whale concentration, liquidity lock and scam lists. Returns a verdict (scam / high_risk / caution / low_risk) with plain-language reasons. 5 free checks per day, then $0.003 per check via x402 (USDC on Base).

Endpoints

URLTransportStateLatencyChecked
https://trust-check.gm-tools.workers.dev/mcp streamable-http answering 1060 ms 10 min ago

Alternatives to Trust Check

same job, measured the same way
Atlas MCP
by atlas26onchain

Base token safety checks (honeypot test, liquidity, new launches), paid per call in USDC via x402.

372 installs/wk local only
Cyberwarex Defi Oracle
by cyberpunk11147

Token safety: honeypot sim, contract powers, rug checks, watch alerts, plain card, paper test.

local only
SMB Sandbox
by teamshift-io

Mock small-business CRM, inbox, calendar, invoicing and phone tools for testing AI agents safely.

200 installs/wk local only
Currents
by currents

Self-healing CI tests and proof of work for AI agents

answering
H
Honeycheck
by honeycheck

Before buying a token on Arc, test whether it can be sold back. Free, or 1-5c a call over x402.

46 installs/wk local only
Kineti
by therawlogs

Kineti: spend cap, undo, and test proof for AI coding agents

326 installs/wk local only
M
marginal
by marginal

Email A/B tests for AI agents: subject lines, managed sends, open/click tracking, and results.

answering
Account Pool
by ankitsxchdeva

Exclusive, crash-safe leases on a pool of test accounts for parallel agent QA runs.

43 installs/wk local only

Trust Check — questions

Answers built from our own checks of this server.

What can Trust Check do?
It exposes 2 tools, read directly from the server on our last check. Among them: check_address_safety, check_token_safety. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Trust Check working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 912 ms. The bar chart above shows every period we have measured.
How do I connect Trust Check?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Trust Check need an API key?
No. Trust Check completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Trust Check?
It answers our handshake in 912 ms on average, which is faster than 9% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.