proomt

Search

Search posts, papers, and topics

All posts

RenderAzzam Aijazi2 min readrelease notesintro

New in Render: Do more with your coding agent

Read on render.com

Summary

Render added browser‑based MCP login and a suite of agent‑friendly actions (service creation, DB queries, log inspection, deploy triggers) plus CLI JSON/YAML output. Build times dropped 60% for Dockerfiles and 25% for Node.js, and new OIDC, SCIM, and logging integrations tighten security and observability.

  • MCP server now supports browser login and exposes actions for coding agents to manage services, query Postgres, view logs, trigger deploys, and clear caches.
  • Render CLI can emit JSON/YAML, making its output easy to consume in automated agent workflows.
  • Median Dockerfile build time fell from ~80 s to ~30 s (‑60%); Node.js native‑runtime builds improved from ~40 s to ~30 s (‑25%).
  • Pro workspaces can use OIDC with Anthropic, OpenAI, AWS, and SCIM fields are expanded; logs can be streamed to Coralogix for centralized observability.

Teams building AI coding agents or automated CI/CD pipelines need tighter integration, faster builds, and secure credential handling to streamline deployment and operations.

5/10
devopsllmobservabilitysecurityperformancepostgres

Related reading

  1. Build, deploy, and operate with coding agents on Render

    Render adds OAuth‑based MCP access, expands its “skills” library to 20+ actions, and upgrades the CLI to manage full service lifecycles, enabling coding agents (Cursor, Claude, Codex, ChatGPT) to trigger deploys, adjust plans, and spin up disposable PR environments via structured JSON/YAML commands.

    Renderrender.com4 min

  2. Reuse builds across multiple services

    Render now lets you reuse a single build artifact across multiple services, cutting duplicate builds and ensuring identical code moves from staging to production. The feature is in private beta, works for web, private, and worker services, and separates build‑time from runtime secrets.

    Renderrender.com2 minrelease

  3. MCP was always a bad idea?

    The author argues that Model Control Protocol (MCP) still has value even with powerful coding agents. MCP lets you control service access, manage authentication safely, provide a UI for connections, and keep audit logs.

    Simon Willisonsimonwillison.net1 minHN11

  4. WebMCP support now available in mcp-handler

    Vercel's mcp-handler 2.2.0 adds experimental WebMCP support, letting you expose registered MCP tools to in‑browser agents via a single script tag. The script proxies tool calls back to your MCP server with the signed‑in user’s credentials, so no extra OAuth flow is needed.

    Vercelvercel.com1 minrelease

  5. Blog: How to Build a DevOps Agent

    This blog walks through the open‑source DevOps Agent Kit, which lets Claude Code or Cursor act as a DevOps assistant by connecting to CloudBees Unify, Jira, and Slack via MCP servers and to GitHub via the CLI. It provides a repeatable setup (Docker, Node, env file) and seven slash commands for pipeline overview, triage, security, release readiness, flag management, CI health scoring, and Jira tic…

    Codeshipcloudbees.com10 min

  6. Give your eve agent a browser

    Vercel released the @agent-browser/eve extension, giving Eve agents full browser automation capabilities inside their sandbox. It adds installable tools for navigation, interaction, and screenshots, with domain allowlists and credential protection.

    Vercelvercel.com1 minrelease