agent_permissions — Warden Token Terminal MCP Tool
agent_permissions
(agent permissions) is one of 12 tools on the
Warden Token Terminal
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call agent_permissions from your client
- Claude Code Warden Token Terminal agent_permissions run in your project directory
- Claude Desktop Warden Token Terminal agent_permissions ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Warden Token Terminal agent_permissions ~/.cursor/mcp.json
- VS Code Warden Token Terminal agent_permissions .vscode/mcp.json
- Zed Warden Token Terminal agent_permissions ~/.config/zed/settings.json
- Windsurf Warden Token Terminal agent_permissions ~/.codeium/windsurf/mcp_config.json
- Cline Warden Token Terminal agent_permissions ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Warden Token Terminal agent_permissions ~/.gemini/settings.json
- Grok Warden Token Terminal agent_permissions .mcp.json (in your project root)
- ChatGPT Warden Token Terminal agent_permissions Settings → Connectors → Advanced → Developer mode
- Claude.ai Warden Token Terminal agent_permissions Settings → Connectors → Add custom connector
- LangChain Warden Token Terminal agent_permissions pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http token-terminal https://tokens.wardenprotocol.org/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 6 November 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.