start_here — MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors MCP Prompt
start_here
is one of 1 prompt on the
MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors
MCP server. Connect the server and it appears in your client, ready to invoke.
by client
How to invoke start_here from your client
- Claude Code MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here run in your project directory
- Claude Desktop MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here ~/.cursor/mcp.json
- VS Code MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here .vscode/mcp.json
- Zed MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here ~/.config/zed/settings.json
- Windsurf MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here ~/.codeium/windsurf/mcp_config.json
- Cline MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here ~/.gemini/settings.json
- Grok MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here .mcp.json (in your project root)
- ChatGPT MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here Settings → Connectors → Advanced → Developer mode
- Claude.ai MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here Settings → Connectors → Add custom connector
- LangChain MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors Prompt/start_here pip install langchain-mcp-adapters
MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors also offers 3 resources — data you attach as context, where a prompt is something you run.
Read from the server itself, by connecting to it and calling prompts/list on 24 September 2026.
A listing does not declare its prompts, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each prompt's arguments.