531 posts tagged with "AI agents"
AI agents and autonomous systems
Kubernetes Shipped a Sandbox API for AI Agents: What a Declarative Singleton-Workload Primitive Means for a Deploy-From-Chat PaaS
SIG Apps' Agent Sandbox CRD collapses the hand-rolled StatefulSet-plus-Service-plus-PVC stack into one declarative resource for stateful AI agent runtimes. Here is how the four CRDs work, what the gVisor-vs-Kata choice costs, and which parts a self-hosted platform should adopt now.
MCP's 10,000-Server Problem: Building an Allowlisted, Audited Tool Catalog Before an Agent Can Deploy to Your Fleet
With 10,000+ public MCP servers and most scanned servers needing security review, connecting an agent to a tool is now a governance problem. A tiered, allowlisted tool catalog design — plus a deploy-from-chat walkthrough — for teams running agents against production.
450+ MCP Servers Catalogued and Quality-Scored Daily: What the Ecosystem Census Says About the Tool Sprawl Your Deploy Platform Inherits
A daily census grades 453 MCP servers an average of 16.3 out of 100. Here is what that number means for platform teams, the security gap the score does not cover, and a bless-or-block rubric for governing tenant agent tools.
MCP Bets H2 2026 on Server Cards: What Your Registry-Less Server Must Hand-Roll Today
The July 2026 MCP spec shipped stateless transport and a mandatory server/discover RPC but left pre-connect Server Cards experimental. Here is the concrete manifest, capability advertisement, and trust signaling a registry-less deploy-from-chat server builds today so the eventual card format is a migration, not a rewrite.
Your Agent Doesn't Need Your API Key: What Qovery's Infrastructure-MCP Play Proves About Governed Tool Interfaces
Qovery's infrastructure-MCP writeup defines the governed alternative to pasting API keys into agents: scoped per-tool authority, server-side budget caps, and a per-call audit trail. What that boundary contains, why it became a product category in 2026, and what self-hosting it on your own machines requires.
Deploy From Chat: What Coolify, Arcade, and Azure APIM Prove About MCP Servers for PaaS Ops
Coolify's community MCP bridge, Arcade's 8,000-tool OAuth runtime, and Azure APIM's REST-to-MCP exposure prove agents can deploy, roll back, and tail logs from chat. The protocol is the easy part — discovery, scoped credentials, and confused-deputy hardening decide whether an agent gets real authority.
Modal's $355M Series C Puts a Price on the Sandbox: What $0.33/Hour Per Agent Sandbox Really Costs vs Self-Hosted
Modal's $355M raise at a $4.65B valuation prices agent sandboxes as their own category. Working through the per-second meter against owned hardware puts the crossover at about 5% utilization — and memory-while-alive metering is the line item that decides it.
Railway Turned Its CLI MCP Server Into a Proxy: One Credential for Every Agent, and an Audit Trail You Can No Longer See
Railway's September 2026 changelog flips railway mcp from a bundled local server to a proxy for its hosted MCP endpoint. Here is the three-way tradeoff — local vs proxy-to-hosted vs self-hosted — across credentials, logging, scope enforcement, and audit ownership, plus a decision rule for production agent access.
Six Coding Agents on a Private Network: Threat-Model the Credential Blast Radius Before You Copy Railway's Sandbox
Railway's June 2026 sandboxes preinstall six coding agents with private-network reach to production data. Four Kubernetes controls — per-session identities, default-deny egress, approval-gated mutations, and auditable teardown — keep the convenience without the nine-second-wipe blast radius.