Dork can now connect to Streamable HTTP MCP servers to discover and
use external tools at runtime. This bridges the gap between dev-time
MCP configs (.mcp.json) and the production AI chat system.
- MCPClient class using @modelcontextprotocol/sdk for full spec support
- useMCPTools hook with TanStack Query caching (5-min stale time)
- MCP tools merged into Dork's tool array and routed through MCPClient
- Settings UI in Advanced Settings to add/remove MCP servers
- MCPServer type, Zod schema, and AppConfig integration
The $follows variable resolver was querying kind 3 (contact list) with a
'#d' filter, but kind 3 is a replaceable event that has no d tag. This
caused the query to return zero results, so the follows list was never
resolved and the author filter was silently dropped.
Only include '#d' in the query filter for addressable events (30000-39999).
Also fix pre-existing lint error (unused useMemo import) and missing
aiModel field in TestApp.
- Extract tool definitions and message types to src/lib/aiChatTools.ts
- Extract system prompt to src/lib/aiChatSystemPrompt.ts
- Extract tool executor hook to src/hooks/useAIChatTools.ts
- Extract session logic to src/hooks/useAIChatSession.ts
- Page reduced from 1086 to 321 lines (render + sub-components only)
- Fix layout: remove overflow-hidden and nested scroll, align with main branch
Lemon