get_roast_result — ROASTED MCP Tool Read-only
get_roast_result
(get roast result) is one of 3 tools on the
ROASTED
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call get_roast_result from your client
- Claude Code ROASTED get_roast_result run in your project directory
- Claude Desktop ROASTED get_roast_result ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor ROASTED get_roast_result ~/.cursor/mcp.json
- VS Code ROASTED get_roast_result .vscode/mcp.json
- Zed ROASTED get_roast_result ~/.config/zed/settings.json
- Windsurf ROASTED get_roast_result ~/.codeium/windsurf/mcp_config.json
- Cline ROASTED get_roast_result ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI ROASTED get_roast_result ~/.gemini/settings.json
- Grok ROASTED get_roast_result .mcp.json (in your project root)
- ChatGPT ROASTED get_roast_result Settings → Connectors → Advanced → Developer mode
- Claude.ai ROASTED get_roast_result Settings → Connectors → Add custom connector
- LangChain ROASTED get_roast_result pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http roasted https://base44.app/api/apps/699732f3fcb10c954f3abac2/functions/roastedAgentMcpOther 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.