# Task ID: 34

**Title:** Connect mcplocal MCP router to mcpd proxy endpoint

**Status:** done

**Dependencies:** 28 ✓, 29 ✓

**Priority:** high

**Description:** Update mcplocal's MCP router to forward tool calls to mcpd's new /api/v1/mcp/proxy endpoint instead of connecting to MCP servers directly.

**Details:**

1. Update `src/mcplocal/src/router.ts` to use mcpd proxy:
   ```typescript
   class Router {
     private mcpdClient: McpdClient;
     
     async handleToolsCall(request: JsonRpcRequest) {
       const { name, arguments: args } = request.params;
       const [serverName, toolName] = name.split('/');
       
       // Pre-process with LLM if enabled
       const processedArgs = this.config.enablePreprocessing
         ? await this.llmProcessor.preprocessRequest(toolName, args)
         : args;
       
       // Call mcpd proxy endpoint
       const result = await this.mcpdClient.post('/api/v1/mcp/proxy', {
         serverId: serverName,
         method: 'tools/call',
         params: { name: toolName, arguments: processedArgs }
       });
       
       // Post-process response with LLM if enabled
       return this.config.enablePreprocessing
         ? await this.llmProcessor.filterResponse(toolName, args, result)
         : result;
     }
   }
   ```
2. Update upstream configuration:
   - Remove direct upstream connections for managed servers
   - Keep option for local/unmanaged upstreams
3. Add server discovery from mcpd:
   ```typescript
   async refreshServerList() {
     const servers = await this.mcpdClient.get('/api/v1/servers');
     this.updateAvailableTools(servers);
   }
   ```
4. Handle tools/list by aggregating from mcpd servers
5. Handle resources/list and prompts/list similarly

**Test Strategy:**

1. Unit test: Tool calls are forwarded to mcpd proxy correctly
2. Unit test: Server name is extracted from namespaced tool name
3. Integration test: Full flow Claude -> mcplocal -> mcpd -> container
4. Test tools/list aggregates from all mcpd servers
5. Test error handling when mcpd is unreachable
6. Test LLM preprocessing is applied when enabled