---
title: "MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?"
category: "talks"
date: "2026-06-30"
time: "3:20pm-3:40pm"
track: "Context Engineering"
room: "Track 8"
speakers: ["Cornelia Davis"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Context Engineering"
scheduleRoom: "Track 8"
scheduleLabels: ["Context Engineering", "Track 8", "session", "confirmed"]
---
# MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?

## Conference Context
- Date/time: 2026-06-30 · 3:20pm-3:40pm
- Track/room: Context Engineering · Track 8
- Speaker(s): Cornelia Davis
- Session type/status: session · confirmed

- Track: Context Engineering
- Room: Track 8
- Session type: session
- Status: confirmed

## Session Description
The November 2025 MCP spec release introduced tasks, a way to make tool calls in an async manner. But more than 5 months later (an eternity in AI-time) there are still NO clients that support it - not Claude, not Codex, not even goose! I believe there are two reasons: Designing the client experience when there are potentially 1000s of background tasks running on their own schedule and engaging humans at unpredictable times is a challenge. And tasks place new infrastructure requirements on such a client. This talk will share the findings from having built against the tasks protocol and will suggest solutions these problems. Yup, we'll have a working client!

## Media Evidence
[OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal](https://www.youtube.com/watch?v=k8cnVCMYmNc) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- Source video: `youtube-k8cnVCMYmNc`
- Slide deck: [[youtube-k8cnVCMYmNc-dense-slides|Dense Slides: OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal]] — 3 visible slide image(s); 3 HTML recreation(s).
![[assets/dense-slides/k8cnVCMYmNc/slide-004.jpg]]
![[assets/dense-slides/k8cnVCMYmNc/slide-006.jpg]]
![[assets/dense-slides/k8cnVCMYmNc/slide-011.jpg]]
- Additional slide evidence: [[youtube-k8cnVCMYmNc-slides|Slides: OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal]], [[youtube-k8cnVCMYmNc-reconstructed-slides|Reconstructed Slides: OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal]]
- Slide-derived themes for `youtube-k8cnVCMYmNc`: note, enough, quota, account, pending, event, types.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
- `youtube-k8cnVCMYmNc` — 2 slide-derived text signals
- Slide-derived themes for `youtube-k8cnVCMYmNc`: note, enough, quota, account, pending, event, types.
- Evidence links for `youtube-k8cnVCMYmNc`: [[youtube-k8cnVCMYmNc]], [[youtube-k8cnVCMYmNc-slides]], [[youtube-k8cnVCMYmNc-dense-slides]], [[youtube-k8cnVCMYmNc-reconstructed-slides]]

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

## People
- [[cornelia-davis]]

## Supporting Slides
- [[youtube-k8cnVCMYmNc-slides]] — extracted from the related public AI Engineer video.

## Slide Evidence
- Slide-only cropped deck: [[youtube-k8cnVCMYmNc-dense-slides]] (11 viable slide images).
- Related slide/OCR pages:
- [[youtube-k8cnVCMYmNc-dense-slides]]
- [[youtube-k8cnVCMYmNc-reconstructed-slides]]
- [[youtube-k8cnVCMYmNc-slides]]
- Slide-derived terms: `temporal`, `completed`, `python`, `tools`, `alerts`, `pycache`, `here`, `result`, `weather`, `openal`, `instructions`, `today`, `york`, `skies`, `clear`, `start_workflow`, `model`, `support`

## Synthesis
### Synthesized Breakdown
# MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async? ## Conference Context - Date/time: 2026-06-30 · 3:20pm-3:40pm - Track/room: Context Engineering · Track 8 - Speaker(s): Cornelia Davis - Session type/status: session · confirmed - Track: Context Engineering - Room: Track 8 - Session type: session - Status: confirmed ## Session Description The November 2025 MCP spec release introduced tasks, a way to make tool calls in an async manner. But more than 5 months later (an eternity in AI-time) there are still NO clients that support it - not Claude, not Codex, not even goose! I believe there are two reasons: Designing the client experience when there are potentially 1000s of background tasks running on their own schedule and engaging humans at unpredictable times is a challenge.

### Speaker And Company Context
- [[cornelia-davis|Cornelia Davis]] — Principal Technologist at [[temporal|Temporal]].

### Topics Covered
- [[agentic-search]]
- [[coding-agents]]
- [[mcp]]

### Derived Links And Source Material
- [[youtube-k8cnVCMYmNc]] — related YouTube source page.
- [[youtube-k8cnVCMYmNc-slides]] — slide evidence.
- [[youtube-k8cnVCMYmNc-reconstructed-slides]] — slide evidence.
- [[youtube-k8cnVCMYmNc-dense-slides]] — slide evidence.

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.