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