74 posts tagged with "Model Context Protocol"
Content about the Model Context Protocol (MCP)
JADEPUFFER Ran a Full Ransomware Kill Chain With No Human Involved — What That Means for Agents That Deploy Your App
An AI agent ran an entire ransomware attack end to end with no human directing a single step. Here's what that kill chain means for any platform whose own agent can deploy or restart your infrastructure.
Kubernetes Wrote the AI Contribution Rulebook. Here's the Cheat Sheet for a One-Person PaaS
Kubernetes' new AI contribution policy leans on CNCF funding most projects don't have — here's which parts are free to copy, and what curl, Ghostty, and tldraw did without that budget.
MCP's Enterprise-Managed Authorization Goes Stable: What the ID-JAG Grant Fixes and What It Doesn't
MCP's Enterprise-Managed Authorization extension went stable in June 2026, killing per-server OAuth consent screens via a new ID-JAG grant flow — but it only governs connections, not individual tool calls, leaving per-action authorization for agent deploy/rollback tools squarely up to the platform.
MCP Goes Vendor-Neutral: What the Linux Foundation Handoff Actually Buys Down
Anthropic handed MCP's governance to a new Linux Foundation body, and the protocol's biggest breaking change yet ships in three weeks. Here's what actually changed, what didn't, and what it means for a platform betting on MCP as its agent interface.
MCP's Sticky-Session Problem Is Over: What the July 28, 2026 Stateless Spec Means for a Deploy-From-Chat MCP Server
MCP's July 28, 2026 spec removes protocol-level sessions entirely. Here's exactly what breaks, what SEP-2567 and the Tasks extension replace it with, and the migration checklist for a self-hosted PaaS's own deploy-from-chat MCP server.
MCP Drops Sticky Sessions: What the July 28 Stateless Spec Actually Removes From Your Infrastructure
The MCP spec finalizing July 28, 2026 deletes the session ID and the handshake. Here's the actual infrastructure a production MCP server gets to delete with it — and the two things that don't get any simpler.
60% of MCP Servers Have Security Issues: The Checklist Before You Expose Deploy/Rollback to an Agent
A July 2026 census scanned 9,695 MCP servers and found 5,832 with security issues. Here's the breakdown and the concrete checklist a deploy-from-chat PaaS needs to clear before letting an agent touch production.
OpenTelemetry's GenAI Semantic Conventions: What Vendor-Neutral Agent Spans Buy Your Own Agent-Ops Telemetry
OpenTelemetry's GenAI spec standardizes how agent frameworks emit spans for LLM calls, tool invocations, and token usage — here's what wiring your own MCP deploy tools to emit them buys a self-hosted platform's agent-ops telemetry.
Pinterest's MCP Registry Handles 66,000 Monthly Tool Calls: The Architecture Behind It
Pinterest's production MCP ecosystem handles 66,000 tool calls a month across Presto, Spark, and Airflow. Here's how its central registry, two-layer auth, and human-in-the-loop gating actually work — and what it means for any platform whose AI-agent tools are about to multiply.