MCP Observatory
github re-analysis due

MrWizardlyLoaf/solguard-mcp

github

On-chain token safety + safe execution MCP for Solana AI agents — detect rugs, honeypots & authority traps, then execute MEV-protected swaps.

maintainer
MrWizardlyLoaf
license
MIT
first seen
2026-06-11
last seen
2026-06-11
releases · 30d
2
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 4 tools
transport streamable-http · http counts 4 tools · 0 res · 0 prompts permission surface via code analysis

tools

  • check_authorities

    mint / freeze / Token-2022 trap detection

  • prepare_optimized_swap

    gas-optimized, MEV-protected swap routing

  • simulate_sell

    can the token actually be sold? (honeypot check)

  • verify_token_safety

    on-chain safety audit (authority, liquidity, holders, honeypot)

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 471caa4 · analyzer v17 · 21h ago

skills & prompt files 1

code evidence vv1.0.1 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

network 1

  • net MrWizardlyLoaf-rugcheck-ai-471caa4/server.py :14 import httpx

declared dependencies 3

  • fastmcp@>=2.0
  • solders@>=0.21
  • httpx@>=0.27