detect_trace_tool_policy — injection detector MCP Tool
detect_trace_tool_policy
(detect trace tool policy) is one of 2 tools on the
injection detector
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call detect_trace_tool_policy from your client
- Claude Code injection detector detect_trace_tool_policy run in your project directory
- Claude Desktop injection detector detect_trace_tool_policy ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor injection detector detect_trace_tool_policy ~/.cursor/mcp.json
- VS Code injection detector detect_trace_tool_policy .vscode/mcp.json
- Zed injection detector detect_trace_tool_policy ~/.config/zed/settings.json
- Windsurf injection detector detect_trace_tool_policy ~/.codeium/windsurf/mcp_config.json
- Cline injection detector detect_trace_tool_policy ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI injection detector detect_trace_tool_policy ~/.gemini/settings.json
- Grok injection detector detect_trace_tool_policy .mcp.json (in your project root)
- ChatGPT injection detector detect_trace_tool_policy Settings → Connectors → Advanced → Developer mode
- Claude.ai injection detector detect_trace_tool_policy Settings → Connectors → Add custom connector
- LangChain injection detector detect_trace_tool_policy pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcpOther tools on this server
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.