266 posts tagged with "Model Context Protocol"
Content about the Model Context Protocol (MCP)
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.
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.
Agents Will Operate Your Platform With or Without You: What Frigade's Show HN Proves About Agent APIs
A 96-point Show HN turned observed web traffic into agent tools. That demand signal leaves platforms one choice: ship a versioned, scoped, auditable agent interface, or inherit reverse-engineered traffic with none of those properties.
Your CI Server Just Became an Agent Tool: What TeamCity's MCP Server Means for Deploy-From-Chat
TeamCity's MCP servers — the community's 87-tool Full Mode and JetBrains' official 2026.1 endpoint — turn builds, tests, and agent pools into agent-callable tools. The CI half of deploy-from-chat is here; per-tool scoping and human approval decide whether it is safe to use.
X Ships a Hosted MCP Server, and Agent Access Is Now Table Stakes
X's hosted MCP server joins Slack, Notion, GitHub, and Stripe in making first-party agent access the default. Here is the concrete production-grade bar — auth, transport, scoping, rate limits — and how it re-sequences your own MCP roadmap.
Who Sent This Agent, and Whose Authority Is It Spending? What the IETF's AIMS Draft Means for MCP Server Auth
The IETF's AIMS draft composes WIMSE, SPIFFE, and OAuth 2.0 into one agent identity model. Here is what a deploy-from-chat MCP server should borrow — and how to prove which agent called and whose authority it spent.
Your REST API Is Already an MCP Server: The Gateway Bridge That Skips the Rewrite (and Where It Breaks)
API gateways can now expose REST operations as MCP tools with no backend rewrite — how Azure APIM's bridge works, what governance comes free, and the five limits that call for a purpose-built MCP server.
Better-PaaS and the 'Agent-First' PaaS Pitch: What a Single-VPS Deploy Tool Gets Right — and Where It Stops at the Second Machine
Better-PaaS puts scoped agent tokens and MCP deploy tools on a single VPS — genuinely good design. A verified inventory of what ships, the principle worth stealing, and the concrete second-machine line where single-box agent surfaces stop and multi-node control planes take over.