Back to Signal Feed
CodeTracked since May 19, 2026

Extend MCP API timeout to 800s to stop 5-minute stream drops

Added an explicit `maxDuration = 800` to both streaming MCP route handlers (`apps/api/src/app/api/agent/[transport]/route.ts` and `apps/api/src/app/api/v2/agent/[transport]/route.ts`), replacing the implicit Vercel default timeout path for these endpoints so MCP sessions can run for about 13 minutes before function recycle.

VercelmaxDuration/api/agent/mcp/api/v2/agent/mcp

What Happened

  • Added an explicit `maxDuration = 800` to both streaming MCP route handlers (`apps/api/src/app/api/agent/[transport]/route.ts` and `apps/api/src/app/api/v2/agent/[transport]/route.ts`), replacing the implicit Vercel default timeout path for these endpoints so MCP sessions can run for about 13 minutes before function recycle.
  • Added an explicit `maxDuration = 800` to both streaming MCP route handlers (`apps/api/src/app/api/agent/[transport]/route.ts` and `apps/api/src/app/api/v2/agent/[transport]/route.ts`), replacing the implicit Vercel default timeout path for these endpoints so MCP sessions can run for about 13 minutes before function recycle.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

This change configures the MCP agent streaming routes with an explicit `maxDuration` value of 800 seconds (Vercel Pro cap), directly preventing platform-default 300-second timeouts from cutting off active Cursor MCP sessions during normal usage.

Why Track This

Why It Matters

Operators and users of Cursor MCP sessions should stop seeing active AI coding sessions drop around 5 minutes, so workflows that rely on long-lived streaming responses can continue without abrupt session interruption. It does this by overriding the default 300-second Vercel timeout with an explicit 800-second budget; after deployment, teams should monitor for residual timeout errors near the new ceiling and verify no regression if sessions legitimately exceed ~13 minutes.

Impact

Operators and users of Cursor MCP sessions should stop seeing active AI coding sessions drop around 5 minutes, so workflows that rely on long-lived streaming responses can continue without abrupt session interruption. It does this by overriding the default 300-second Vercel timeout with an explicit 800-second budget; after deployment, teams should monitor for residual timeout errors near the new ceiling and verify no regression if sessions legitimately exceed ~13 minutes.

What To Watch Next

  • Watch whether Vercel becomes a repeated pattern.
  • Track follow-up changes around LLMOps.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: watch_sessions_nearing_800_seconds, verify_vercel_plan_timeout_limits_stay_consistent.
Open Topic TimelineOpen Technical EventOpen Original Sourcewatch_sessions_nearing_800_seconds / verify_vercel_plan_timeout_limits_stay_consistent / monitor_new_timeout_error_traces_for_cursor_clients

Supporting Evidence

GITHUB PULL REQUESTHigh Trust

superset-sh/superset PR #4709: fix(api): add maxDuration=800 to MCP agent routes to prevent 300s timeout

Vercel was terminating `/api/agent/mcp` and `/api/v2/agent/mcp` sessions at 300 seconds with `Vercel Runtime Timeout Error: Task timed out after 300 seconds`, producing 83,539 errors since 2026-05-01 and 75–1,452/hour.