fix(gateway): defer mcp loopback imports

CHANGELOG.md

@@ -53,6 +53,7 @@ Docs: https://docs.openclaw.ai
 - Gateway/startup: move chat run/subscriber registries onto a lightweight state module and defer chat/session event projection until the first event so Gateway boot skips session IO imports. Thanks @vincentkoc.
 - Gateway/startup: keep node session runtime on a lightweight JSON parser instead of importing gateway method validation helpers during boot. Thanks @vincentkoc.
 - Gateway/startup: read embedded-run activity from a lightweight shared state module so restart deferral no longer imports the embedded runner during Gateway boot. Thanks @vincentkoc.
+- Gateway/startup: defer MCP loopback server imports until Gateway shutdown so normal boot no longer loads the loopback HTTP/tool schema stack just to register close handlers. Thanks @vincentkoc.
 - CLI/Gateway: use a parse-only config snapshot for plain `gateway status` reads and reuse same-path service config context so status no longer spends tens of seconds in full config validation before printing. Thanks @vincentkoc.
 - Lobster/Gateway: memoize repeated Ajv schema compilation before loading the embedded Lobster runtime so scheduled workflows and `llm.invoke` loops stop growing gateway heap on content-identical schemas. Fixes #71148. Thanks @cmi525, @vsolaz, and @vincentkoc.
 - Codex harness: normalize cached input tokens before session/context accounting so prompt cache reads are not double-counted in `/status`, `session_status`, or persisted `sessionEntry.totalTokens`. Fixes #69298. Thanks @richardmqq.

src/gateway/server.impl.ts

@@ -46,7 +46,6 @@ import {
 } from "../tasks/task-registry.maintenance.js";
 import { createAuthRateLimiter, type AuthRateLimiter } from "./auth-rate-limit.js";
 import { resolveGatewayAuth } from "./auth.js";
-import { closeMcpLoopbackServer } from "./mcp-http.js";
 import { createGatewayAuxHandlers } from "./server-aux-handlers.js";
 import { createChannelManager } from "./server-channels.js";
 import { createGatewayCloseHandler, runGatewayClosePrelude } from "./server-close.js";
@@ -125,6 +124,11 @@ function getChannelRuntime() {
   return cachedChannelRuntime;
 }
 
+async function closeMcpLoopbackServerOnDemand(): Promise<void> {
+  const { closeMcpLoopbackServer } = await import("./mcp-http.js");
+  await closeMcpLoopbackServer();
+}
+
 const logHealth = log.child("health");
 const logCron = log.child("cron");
 const logReload = log.child("reload");
@@ -593,7 +597,7 @@ export async function startGatewayServer(
       stopModelPricingRefresh: runtimeState.stopModelPricingRefresh,
       stopChannelHealthMonitor: () => runtimeState?.channelHealthMonitor?.stop(),
       clearSecretsRuntimeSnapshot,
-      closeMcpServer: async () => await closeMcpLoopbackServer(),
+      closeMcpServer: closeMcpLoopbackServerOnDemand,
     });
   const { getRuntimeSnapshot, startChannels, startChannel, stopChannel, markChannelLoggedOut } =
     channelManager;