266 posts tagged with "Model Context Protocol"
Content about the Model Context Protocol (MCP)
Deploy From Chat Without Handing the Agent Your Production Keys: Remote MCP After the 2026-07-28 Spec
A production design for a deploy-capable remote MCP server under the 2026-07-28 spec: OAuth discovery via protected-resource metadata, audience-bound tokens, narrow per-environment scopes, human approval gates for destructive tools, and chain-complete audit logs.
Stripe's Agentic Provisioning Protocol Puts Railway One CLI Command Away — and Draws the Line Where MCP Stops
Stripe's Agentic Provisioning Protocol takes agents from nothing to a running Railway resource — account, $5 trial, credentials, Postgres — in one CLI flow MCP cannot express. How discovery, authorization, and tokenized payment work under the hood, and a seven-item checklist for the self-hosted equivalent.
CIS Shipped the First MCP Server Benchmark: A 10-Domain Hardening Checklist Before Agents Get Production Credentials
The CIS MCP Server Benchmark v1.0.0 packs 55 recommendations into 10 security domains — here is each domain mapped to a concrete pass/fail check for a self-hosted PaaS deploy/operate surface, plus the four gaps to close before agent credentials touch production.
MCP Won: Why Every Major AI Vendor Shipping One Protocol Makes 'Deploy From Chat' a Safe Roadmap Bet
Anthropic, OpenAI, Google, Microsoft, and Amazon all ship MCP now — 97M monthly SDK downloads, 10,000+ servers, neutral foundation governance. What that convergence changes about betting your platform's deploy/rollback/logs agent surface on one protocol, and the four residual risks to budget for.
MLflow's MCP Registry: Versioned, Governed Tool Dependencies for Production Agents
MLflow 3.15.0's experimental MCP Registry versions MCP servers with semver, promotes them through staging and production aliases, snapshots their tools, and links traces to exact versions — a worked walkthrough of the promotion loop, the registry-vs-gateway boundary, and when a second tenant makes the catalog mandatory.
Ship the Agent, Not Just the App: Curie vs Deployah and the Future of the Git-Push Deploy Contract
Curie ships Claude Code agents to Kubernetes via git push while Deployah shrinks the manifest to a short spec with nothing in-cluster: a side-by-side of the two deploy contracts, the six deploy-time concerns agents add, and which end a git-push PaaS should extend first.
CIS Published the First MCP Server Hardening Baseline — Here's What It Demands of Deploy-From-Chat Tools
CIS released the first consensus hardening baseline for MCP servers on September 16, 2026: 55 recommendations across 10 domains. Here is how each domain maps onto MCP tools that deploy, roll back, and read secrets — what a sane self-hosted surface already passes, and what still needs building.
Coolify and Dokploy Are 'Not Designed for AI Agent Auto Deploy': What the HN Verdict Gets Right 6 Months Later
Six months after Hacker News declared Coolify and Dokploy 'not designed for AI agent auto deploy,' we score both tools against MCP-first rivals on six agent-operability dimensions — and show what it actually takes to hand the 2am rollback to an agent.
Crossplane's Case for API-First Infrastructure: What an AI Agent That Deploys Actually Needs From an API
Crossplane's CNCF graduation made composable infrastructure APIs mainstream, but an agent that deploys needs a contract shape — schema, desired state, status, watch, safe retry — not a specific framework. A head-to-head of composite resources against a purpose-built deploy API, with a decision rule for which to build.