529 posts tagged with "AI agents"
AI agents and autonomous systems
454 MCP Servers Catalogued and Quality-Scored Daily: Finding a Production-Grade Server in a Flood of Demos
A daily automated scan catalogues 455 MCP servers and scores them on hygiene — average 16 out of 100. What the data reveals about supply, churn, and how to vet servers before your agents call them.
Five MCP Launches in Five Days — and the Deploy Surface Still Missing
Between September 14 and 18, Rubrik, Algolia, Google, ReleasePad, and the UN all shipped MCP servers — each with governance baked into the protocol layer. Deploy infrastructure is the surface still missing, and third-party servers are already defining it.
MCP Went Stateless: What the 2026-07-28 Spec Means for Long-Running Deploy Tools
MCP revision 2026-07-28 drops sessions, handshakes, and server-initiated requests. A migration map for deploy-from-chat servers whose minute-long tools must rebuild on Tasks, multi-round-trip confirmations, and an explicit task store.
MCP Is the Transition Technology: What Infrastructure-First Enterprise AI Means for Your Deploy API
Enterprises stopped asking which model to pilot and started standardizing how agents reach production systems, with MCP as the emerging standard shape. Here is what that shift validates for a self-hosted deploy API — and which enterprise demands to adopt or skip on day one.
MCP Won the Interface War: What 10,000 Servers and 97M Downloads Mean for Your Self-Hosted Endpoint
MCP passed 10,000 public servers and 97M monthly downloads under neutral Linux Foundation governance, but registries, managed gateways, and vendor defaults are the new lock-in surface. Here is the case for running your deploy-authority endpoint on infrastructure you own.
No More Self-Hosted Git After 15 Years: What AI Actually Changed About the Self-Hosting Calculus
A veteran Linux developer shut down his public git server after 15 years because AI scrapers killed it — then watched the eulogy hit 298 points on Hacker News. His real reason, the two AI pressures behind it, and a keep/move/hedge framework for deciding what stays on your own machines.
One Sandbox API for E2B, Modal, Vercel, and Kubernetes: What Capability Negotiation Actually Buys You
Open Sandbox Router puts one API over E2B, Modal, Vercel Sandbox, Daytona, and your own Kubernetes cluster, placing each sandbox by declared capabilities, cost, and live health. This evaluation walks through the mechanism, the 2026 pricing math, the two failover regimes — and the isolation differences no router can hide.
15,465 MCP Servers, 0 Governance: What OX Security's Census Means for Your Deploy Tools
OX Security mapped 15,465 MCP servers and found agents reaching China, Russia, home networks, and six abandoned domains buyable for $4. The four findings with exact numbers, the Always-Allow attack chain, and a control matrix for governing deploy agents' tools.
Read-Only by Default: The 5-Rung Agent Permissioning Ladder Every Deploy Platform Should Copy
Qovery's agent stack splits deploys from ops and ships its MCP server read-only — with a CLI allowlist and Rego policy tokens above and below. How the five-rung ladder works, where agent-side enforcement breaks, and the checklist for deploy-from-chat on machines you own.