MCP Tasks (async): Why Aren't Any Agents Supporting Them? — Cornelia Davis, Temporal
MCP tasks is a standard that enables AI agents to initiate long-running jobs that can be paused, reported on, and resumed without losing their work—for example, invoice processing that can wait for human approval mid-process.
Cornelia Davis, an expert in distributed systems, demonstrates how this solves a real problem: when networks fail or processes crash during a long-running job, context is often lost. The specification uses a stateless core with long-running behavior as an extension, and allows the server to send updates to the client instead of the client constantly polling. Despite the technology being available, almost no AI agent supports it yet, partly because implementing long-running work correctly is difficult.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More to read
Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation
Techmeme 3 h ago
DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions
Techmeme 3 h ago
Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash
Techmeme 3 h ago
One word for AI agents in 2027
Nate Herk 7 h ago