Skip to content

Cloudflare pushes Workers error alerts straight to MCP agents

The Cloudflare API MCP server now streams Workers Issues as signed webhook events, so an agent can react to a production failure without polling for it.

Source: Cloudflare

Cloudflare’s API MCP server can now push Workers Issues out as MCP Events, according to a changelog post published on 13 October. Workers Issues already detects production failures in a Worker and groups related ones together without needing an SDK or an application wrapper. This release changes how you find out about them: instead of checking a dashboard, you get told.

An MCP client discovers the new event, cloudflare.alert.workers_observability_real_time_issue, through events/list, then subscribes with events/subscribe, scoped to an account or a single Worker. When Issues flags something new or recurring, the server posts a signed event to the client’s webhook. Setting it up means enabling Issues on the Worker, then connecting to https://mcp.cloudflare.com/mcp with Notifications Write and Workers Observability Write permissions.

Why it matters: this is the difference between an agent that has to poll logs and one that gets paged. If you’re already running a coding or ops agent against your Workers, this closes the loop between a production failure and an agent looking at it, without you writing the polling logic yourself.

The caveat: it only works with MCP clients that support the Events spec and webhook delivery, so check your client before assuming this just works.

Share

Related reading

ML for Web Devs

Tokens, context windows, and why your bill is what it is

The unit of billing for language models is not the request or the word. Once you understand tokens and how a context window fills up, the invoice stops being a surprise.

ML for Web Devs

RAG is just search with extra steps

Retrieval-augmented generation gets written up like an architecture. It is a search query, a string concatenation and one API call, and the search query is the part that decides whether it works.

ML for Web Devs

A prompt is a spec, so write it like one

Prompt engineering has very little to do with magic words. It is the same skill as writing a clear ticket for a capable contractor who will not ask you any questions.

More from The Wire

All briefs

Anthropic cuts distillation attacks on Claude by up to 99%

New safeguards, including a reasoning classifier and stricter account limits, now block most attempts to copy Claude by training on its output. Blocked requests in high-confidence cases are billed, and some integrations may need updating.

via Anthropic