Agent Safe for Claude.ai
io.github.wowcool/agentsafe
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
client:Claude.ai
transport:streamable-http
Install Agent Safe in Claude.ai
Settings → Connectors → Add custom connector
https://agentsafe.locationledger.com/mcpClaude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs