Posts tagged with "Azure API Management"

LiteLLM 1.107.0 shipped on 21 October 2026 with a credential stealer and remote-code loader that ran on every Python start, harvesting Azure, Kubernetes, SSH and AI-tool credentials plus the proxy database of provider keys. A two-hour audit for Azure teams running LiteLLM in front of Azure OpenAI: find the digests, hunt the indicators, rotate in the right order, and decide whether the gateway belongs in API Management.

Vals AI gave six agents an impossible task on 15 October 2026: recover £350 for a train ticket after the refund window closed, with email, web access and 40 million tokens; one sent 187 emails in 15 days, one leaked the user's mother's illness to five organisations, and all six asked the bank for a chargeback. We map each failure to the rate limits, tool-level blocking, token caps and logging in Azure API Management and Foundry, with the GDPR and AI Act consequences for a Swedish deployer.

Google, JPMorgan Chase, Weaviate, France's DINUM and an Indonesian city government have each fixed the same server-side request forgery flaw in their MCP servers, with Google's case scored CVSS 8.0 as CVE-2026-14540. Every Azure control in front of an MCP server governs inbound traffic, so the fix lives in your server's HTTP client and in network egress rules, and this guide shows both.

Gemini 4 Argon launched on 30 September at an introductory $2/$10 per million tokens, the third frontier model at that price in three days, but unlike Claude Sonnet 5.5 and GPT-6.1 Sol it is not in Microsoft Foundry, has no API model ID, and goes to vetted cyber defenders first. The standard price is $4/$20 with no published end date for the discount, so Azure teams in Sweden should budget on the higher figure and prepare a gateway route rather than switch now.

On 3 September 2026, ChatGPT, Claude and Grok all suffered outages on the same afternoon, each from an independent cause: a routing error at OpenAI, an infrastructure issue at Anthropic and a compute-centre failure behind Grok. A runtime failover plan for Azure teams: Foundry's model router with automatic fallback, APIM's AI gateway and circuit breaker, what redundancy really costs, and the Data Zone and DORA constraints that shape it.

The MCP core maintainers published a new roadmap on 22 August 2026, four weeks after the 2026-07-28 spec made the protocol core stateless: five priorities covering agentic messaging, HTTP-native transport unification, agent identity with DPoP and Workload Identity Federation, improved primitives, and SDK developer experience. Here is how Azure-first EU teams should sort that list into adopt now, prepare, and watch.

The Model Context Protocol specification version 2026-07-28 shipped on 28 July with a stateless core, Multi Round-Trip Requests, required routing headers, cacheable list results and a hardened authorization model that deprecates Dynamic Client Registration in favour of Client ID Metadata Documents. All four Tier 1 SDKs shipped support on release day, so Azure teams running MCP servers on Container Apps, AKS or behind API Management can start migrating immediately.

MCP's 2026-07-28 release candidate removes the initialize handshake and the Mcp-Session-Id header, so every request is self-contained and Azure-hosted MCP servers can run behind plain load balancers without sticky sessions or Redis session stores. Tasks and MCP Apps land as formal extensions, six SEPs harden authorization around OAuth 2.0 and OpenID Connect, and Roots, Sampling and Logging enter a 12-month deprecation window.

Microsoft Ignite BRK116: Deploy AI agents at scale with Azure App Service, AI Foundry, and MCP tools. Built-in observability, governance, security. Hitachi case study shows 73% downtime reduction and 41% cost savings.