tooltrust-directory

AgentSafe-AI/tooltrust-directory
★ 3 stars Go AI/LLM Updated 7d ago
Trust layer for AI Agents. A curated registry of secure tools and MCP servers with A-F risk grading.
View on GitHub → Try with Claude — $10 free →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "tooltrust-directory": {
      "command": "go",
      "args": [
        "run",
        "github.com/AgentSafe-AI/tooltrust-directory@latest"
      ]
    }
  }
}

README Excerpt

> **This repo hosts [tooltrust.dev](https://www.tooltrust.dev/) — the website and pre-scanned report data. If you want to scan your own MCP servers, go to [tooltrust-scanner](https://github.com/AgentSafe-AI/tooltrust-scanner).** A public registry of AI agent tools, continuously scanned for prompt injection, data exfiltration, and privilege escalation by [ToolTrust Scanner](https://github.com/AgentSafe-AI/tooltrust-scanner).

Tools (14)

ALLOWBLOCKCriticalFeatureHighInfoLowMediumREQUIRE_APPROVALtooltrust_list_rulestooltrust_lookuptooltrust_scan_configtooltrust_scan_servertooltrust_scanner_scan

Topics

agent-safetyai-securitymcpmodelcontextprotocolprompt-injectionsupply-chain-securitytool-directory