canary

JoyTiefling/canary
★ 0 stars Python AI/LLM Updated today
Trust verdict for open-source repos & bounties before you engage — ENGAGE / CAUTION / AVOID / UNKNOWN. CLI + MCP server for agents. Never says "go" on missing data.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "canary": {
      "command": "uvx",
      "args": [
        "canary"
      ]
    }
  }
}

Or install with pip: pip install canary

README Excerpt

**Should I — or my agent — engage with this repo or bounty, or is it a trap?** <!-- mcp-name: io.github.JoyTiefling/canary --> Canary gives a fast trust verdict — `ENGAGE` / `CAUTION` / `AVOID` / `UNKNOWN` — for a GitHub repository or bounty *before* you sink hours (or tokens) into it. Surface trust signals are gameable and now routinely AI-faked. Stars are bought,

Topics

ai-agentsbountiesclideveloper-toolsmcpsecurity