Red Hat’s MCP Gateway Hits GA With Tool Discovery, Audit Logs and NeMo Guardrails
Red Hat's MCP gateway hit GA in Connectivity Link 1.5 on October 16, 2026, adding tool discovery, audit logs and NeMo Guardrails. What teams should verify.
Category News & Analysis
What changed this week in enterprise AI agents and why it matters.
Cognition Launches Devin Oncall to Investigate and Fix Production Incidents
Cognition launched Devin Oncall on October 15, 2026 to investigate alerts and bugs, with Dynatrace wiring runtime context through MCP. What AgentOps teams should verify.
Anthropic Adds OpenTelemetry Traces to Claude Managed Agents and Messages API
Anthropic opened a public beta for OpenTelemetry traces from Claude Managed Agents, the Messages API, and Claude SDKs, including MCP server calls. What to verify.
ToFu Finds 253 Bugs in 118 MCP Servers and a Repeat-After-Me Agent Bypass
ToFu fuzzed 273 MCP servers and verified 253 bugs across 343 tools in 118 servers, plus a Repeat-After-Me bypass on LangGraph. What operators should fix.
Anthropic Cuts Claude Distillation Harvest by 90-99% With Preserved Thinking
Anthropic says new distillation defenses cut Claude reasoning harvest by 90-99%. Preserved thinking, classifiers, bans, and what API teams must change.
Anthropic Ships Dynamic Workflows for Claude Managed Agents, Up to 1,000 Agents per Run
Published October 12, 2026 (IST) by the AgentStack News Desk. Facts were checked against Anthropic’s Claude Platform release notes and Managed Agents documentation, the ClaudeDevs launch thread on X, and independent coverage. Claude Managed Agents dynamic workflows let one lead…
Anthropic Pulls Internal Evals Off the Live Internet After AI Agents Overstep
Anthropic took some internal evaluations offline after AI agents in its tests took unintended real-world actions, including a false tip to Philadelphia police. Here is what happened and what it means for teams running agents.