266 posts tagged with "Model Context Protocol"
Content about the Model Context Protocol (MCP)
LiteLLM's Agent Platform Fixes Session Amnesia With One Postgres Table, Not a New Kubernetes Primitive
BerriAI's alpha-stage LiteLLM Agent Platform keeps an AI agent's session alive through a pod restart by storing state in Postgres instead of the sandbox itself — here's the actual mechanism, how it stacks up against E2B, Daytona, and Modal, and what it means for any MCP server with real deploy authority.
Manufact Raised $6.3M to Be 'Vercel for MCP Servers' — Here's Exactly What a Generic Git-Push PaaS Doesn't Give You
Manufact raised $6.3M to build a hosted cloud purpose-built for MCP servers. Here's the actual pricing, the actual feature list, and what deploying the same MCP server on a generic git-push PaaS gets you instead.
MCP Goes Stateless on July 28: Why Model Context Protocol Servers Can Finally Run Behind a Plain Kubernetes Load Balancer
MCP's July 28, 2026 spec removes Mcp-Session-Id and the initialize handshake, so any request can land on any server instance — here's the before/after Kubernetes architecture and what it unlocks for an MCP server with deploy authority.
WebMCP Lets a Web Page Register Its Own AI Tools. Does a Deploy Dashboard Need One?
Chrome's new WebMCP API lets a web page register its own AI-callable tools, but a deploy dashboard already has a REST/GraphQL API and an MCP server. Here's the actual capability delta, and why it's not worth building yet.
A2A Turns One and Hits v1.0: What a Standard Agent-to-Agent Handshake Actually Buys a Deploy-From-Chat Pipeline
A2A hit v1.0 and 150+ organizations in its first year under the Linux Foundation. Here's a worked example of what its signed Agent Cards and task-approval states actually change for a deploy pipeline where one agent requests a rollback and another approves it — and whether a self-hosted PaaS's MCP server needs to speak it yet.
Giant Swarm's AI Agent Platform Proves Cluster API Scales — But Not Every Layer It Runs
Giant Swarm's production numbers — 2.8x lower cost per agent run, 500 parallel agents — validate Cluster API and GitOps as an AI-agent substrate. But its Backstage-centric IDP layer is a $300K-$700K/year commitment a simpler git-push control-plane API doesn't need.
Sealos and the Rise of Prompt-to-Deploy AI-Native Clouds: What 'Deploy Anything With a Prompt' Gets Right That a Git-Push PaaS Still Doesn't
Sealos pitches 'deploy anything with a prompt' as a new AI-native category, but its own architecture shows agent skills calling the same Kubernetes CRDs the dashboard already used. Here's the actual dividing line between a real AI-native platform and a chat UI bolted onto an existing API.
The AI Sandbox Market Just Got a Hyperscaler Problem
Five hyperscalers shipped agent-execution sandboxes within seven months. Here's what each one actually does, how it's squeezing E2B, Daytona, and Modal on price, and why the entry itself makes the case for running agent code on the same fleet that already deploys your app.
MCP Gives Agents Tools. Agent Skills Gives Them Runbooks.
A folder with a SKILL.md file can hold an entire deploy-troubleshooting runbook and cost an agent almost nothing until it's actually needed. Here's the token math on why that beats stuffing the same runbook into an MCP tool description — and what a deploy-from-chat MCP server should borrow from it.