Skip to main content
Glama

πŸ• GuardDog MCP β€” AgentTradeGuard

Check if a token is SAFE before your AI agent trades it. One call: PASS / WARN / BLOCK (BITE!).

MCP server for AgentTradeGuard β€” agent-first token safety: honeypot detection, contract audit, liquidity structure, P95 23ms verdicts. Powered by the same 4-source engine as the public API: GoPlus + Etherscan V2 + DEX Screener + honeypot.is, served live from api.guarddog.top β€” always fresh, zero local keys.

Source & issues: github.com/guarddog-top/mcp-server-guarddog Β· Prefer REST? api.guarddog.top/v1/check

You:  "check 0x0E09FaBB73Bd3Ade0a17ECC321fD13a19e81cE82 on bsc before I buy"
Dog:  βœ… PASS β€” risk_score 0, no honeypot flags, pool healthy
      (or) 🦴 BLOCK: sell_tax 99%, pool age 2d, honeypot flagged β€” DO NOT TRADE

Quickstart β€” 3 lines, verified in 3 seconds (no Python, no MCP client)

npx -y guarddog-mcp --smoke
# πŸ• GuardDog SMOKE PASS β€” WETH on eth | risk_score=0 | 180ms

That just ran a real check against the live API. Install verified.

Related MCP server: crypto-inspector-mcp

Install β€” Claude Desktop / Cursor / any MCP client

{
  "mcpServers": {
    "guarddog": {
      "command": "npx",
      "args": ["-y", "guarddog-mcp"]
    }
  }
}

First run prepares a shared Python env (~10s, needs Python 3.10+), after that every start is instant. No API key needed β€” free during beta. Stuck on Python? npx -y guarddog-mcp --smoke works without it, and the plain REST API needs nothing but curl.

The one tool

check_address(chain, address, action="swap")
  chain:   "eth" | "bsc" | "solana"
  address: token contract / pool address (0x... or solana base58)
  action:  "swap" (default) | "approve"

Returns:

{
  "risk_score": 97,
  "verdict": "BLOCK",
  "reasons": ["sell_tax 99%", "pool age 2d", "honeypot flagged"],
  "covered": false,
  "data_limited": false,
  "unknown_token": false
}

Verdict semantics (write this into your agent's trading flow):

Verdict

Meaning

Agent should

PASS

safe to proceed

proceed

WARN

suspicious β€” read reasons[]

half-size entry or pass

BLOCK

honeypot / rug pattern

do NOT trade

unknown_token=true

no on-chain footprint

treat as WARN

data_limited=true

a source was down

treat with caution

Call check_address before every buy/approve. A verdict after the trade is an autopsy, not a check.

Prefer REST? (10-second version)

curl "https://api.guarddog.top/v1/check?chain=bsc&target=0x0E09FaBB73Bd3Ade0a17ECC321fD13a19e81cE82"

Free beta: 50 checks/day/IP, no signup. Full spec: guarddog.top/llms.txt

Why GuardDog

  • 4 live sources, fan-out parallel β€” GoPlus (honeypot flags/taxes), Etherscan V2 (contract audit), DEX Screener (pool age/depth), honeypot.is (simulated buy-sell)

  • Validated: ACM SolRPDS dataset, 116,304 labeled rug pulls, 100% coverage

  • Graceful degradation: a source down β†’ data_limited flag, never a hang, never a softened verdict

  • Agent-first errors: every error message carries an executable hint

  • Chains: ETH / BSC / Solana

Requirements

  • Node β‰₯ 18 (the npx launcher)

  • Python β‰₯ 3.10 (the engine; macOS: brew install python@3.12, Ubuntu: apt install python3.12)

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Pre-trade token safety check for AI agents. Simulates a sell before you buy, then reports honeypot, tax, liquidity, pair age, same-ticker impersonation and owner powers as one low/medium/high/unknown verdict. Fail-closed: when a critical check cannot run it answers unknown rather than guessing low. Publishes its own measured error rate with the benchmark harness in the repo.
      3
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables MCP hosts and AI agents to request pay-per-call token risk assessments for contract addresses across Base, Ethereum, and Solana, returning a verdict, 0–100 risk score, six market-structure signals, and an analyst summary, with payment handled via x402 USDC on Base.
      1
      MIT