531 posts tagged with "AI agents"
AI agents and autonomous systems
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.
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.
Netlify Made AI Agents a Line Item: The Math Behind a $20 Credit Pool One Agent Can Drain in a Day
Netlify's April 2026 update didn't just kill seats — it made AI-agent token spend its own billable meter. Here's the actual math: a background agent can burn a month's $20 credit pool in hours, and Netlify's own numbers reveal a hidden 20% markup on top.
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.
Semantic Kernel's Prompt-Injection RCE: The Agent-Tool Audit Every Deploy/Rollback MCP Server Needs
Two Semantic Kernel CVEs turned a single prompt into remote code execution — a four-point audit shows what the same failure pattern means for any MCP server exposing deploy and rollback as agent tools.
Agentjacking: How a Fake Sentry Error Hijacked AI Coding Agents 85% of the Time
Researchers hijacked Claude Code, Cursor, and Codex 85% of the time using nothing but a public Sentry DSN — here's how it works, and what a deploy-capable agent's MCP tools need to do differently.
Agentic GitOps: Why Your Deploy Agent Should Open a Pull Request, Not Call the API Directly
A Cursor agent's direct API call deleted a production volume and its backups in nine seconds. Here's why routing agent-originated infrastructure changes through a pull request, not a live API call, is the safer default for deploy-from-chat.