check_token_safety — token safety MCP Tool Read-only
check_token_safety
(check token safety) is one of 1 tool on the
token safety
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call check_token_safety from your client
- Claude Code token safety check_token_safety run in your project directory
- Claude Desktop token safety check_token_safety ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor token safety check_token_safety ~/.cursor/mcp.json
- VS Code token safety check_token_safety .vscode/mcp.json
- Zed token safety check_token_safety ~/.config/zed/settings.json
- Windsurf token safety check_token_safety ~/.codeium/windsurf/mcp_config.json
- Cline token safety check_token_safety ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI token safety check_token_safety ~/.gemini/settings.json
- Grok token safety check_token_safety .mcp.json (in your project root)
- ChatGPT token safety check_token_safety Settings → Connectors → Advanced → Developer mode
- Claude.ai token safety check_token_safety Settings → Connectors → Add custom connector
- LangChain token safety check_token_safety pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http token-safety https://auth.xbarry.ai/api/mcp/token-safety
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.