build_character_prompts — Canonsheet MCP Tool
build_character_prompts
(build character prompts) is one of 1 tool on the
Canonsheet
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call build_character_prompts from your client
- Claude Code Canonsheet build_character_prompts run in your project directory
- Claude Desktop Canonsheet build_character_prompts ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Canonsheet build_character_prompts ~/.cursor/mcp.json
- VS Code Canonsheet build_character_prompts .vscode/mcp.json
- Zed Canonsheet build_character_prompts ~/.config/zed/settings.json
- Windsurf Canonsheet build_character_prompts ~/.codeium/windsurf/mcp_config.json
- Cline Canonsheet build_character_prompts ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Canonsheet build_character_prompts ~/.gemini/settings.json
- Grok Canonsheet build_character_prompts .mcp.json (in your project root)
- ChatGPT Canonsheet build_character_prompts Settings → Connectors → Advanced → Developer mode
- Claude.ai Canonsheet build_character_prompts Settings → Connectors → Add custom connector
- LangChain Canonsheet build_character_prompts pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http canonsheet https://canonsheet.kaneky.dev/mcp
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.