selftest — authenticated multi llm agent MCP Tool
selftest
(selftest) is one of 2 tools on the
authenticated multi llm agent
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call selftest from your client
- Claude Code authenticated multi llm agent selftest run in your project directory
- Claude Desktop authenticated multi llm agent selftest ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor authenticated multi llm agent selftest ~/.cursor/mcp.json
- VS Code authenticated multi llm agent selftest .vscode/mcp.json
- Zed authenticated multi llm agent selftest ~/.config/zed/settings.json
- Windsurf authenticated multi llm agent selftest ~/.codeium/windsurf/mcp_config.json
- Cline authenticated multi llm agent selftest ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI authenticated multi llm agent selftest ~/.gemini/settings.json
- Grok authenticated multi llm agent selftest .mcp.json (in your project root)
- ChatGPT authenticated multi llm agent selftest Settings → Connectors → Advanced → Developer mode
- Claude.ai authenticated multi llm agent selftest Settings → Connectors → Add custom connector
- LangChain authenticated multi llm agent selftest pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http authenticated-multi-llm-agent https://anthropic-google-auth-oauthlib-mc-70ac16.getvda.ai/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.