MCP

Cline open-sourced the runtime behind its extension and CLI as the Cline SDK, then rebuilt the CLI on top with agent teams, cron jobs, connectors, and example apps. The harness score gives teams a new reference point if they want to compare agent tooling on Terminal-Bench 2.0.

Notion opened a developer platform with an External Agents API plus Workers, webhooks, and a headless CLI. The release lets external agents query Notion, extend workflows, and stay in sync with other systems.

Claude Code 2.1.136 introduced unconditional auto-mode deny rules and fixed several MCP/session failures, including disappearing servers after /clear and lost refresh tokens during concurrent refreshes. The release matters because unattended agent runs can now be constrained more explicitly and remote MCP sessions should require fewer reauths or mid-run recoveries.

TinyFish opened its Search and Fetch features for free with generous rate limits across REST, MCP, CLI, and SDKs. The change gives agent builders cheaper web retrieval while returning structured search JSON or rendered markdown instead of raw HTML.

Builders shared concrete Symphony, create_agent, and MCP setup guides after arguing that model switching is easy but harness switching is not. The playbooks matter because they make harness engineering more repeatable, so teams can copy tested tooling and integration patterns.

Anthropic released Claude Connectors for Blender, Autodesk Fusion, and other creative apps, exposing commands and file actions through MCP. That lets Claude operate inside existing desktop tools instead of only returning chat instructions.

Claude Code 2.1.121 shipped MCP alwaysLoad, plugin prune, skills search, and multiple multi-GB memory leak fixes. It also changes Bash and system-prompt behavior, which can alter existing harness and tool assumptions.

Kilo Code published a Roo Code migration path ahead of Roo’s May 15 archive, including one-command install, automated file renames, custom-agent conversion, and API key re-auth. Use the guide to map Roo modes, rules, MCP config, and checkpoints into Kilo’s agent and worktree model before the cutoff.

Infisical introduced Agent Vault, an open-source credential proxy that lets agents call APIs, CLIs, SDKs, and MCP servers without directly reading secrets. It matters because teams can keep policy and secret storage outside the agent runtime while still supporting on-prem and cloud deployments.

Anthropic shipped Claude Code 2.1.118 with Vim v and V selection, hooks that can invoke MCP tools, merged usage commands, and an environment variable that blocks updates. The CLI gains tighter terminal editing and better fleet control for teams that pin versions or manage plugin and MCP behavior.

Google added Deep Research and Deep Research Max to the Gemini API with collaborative planning, multimodal inputs, MCP support, and native charts. The agents push cited web-plus-private-data reports into developer workflows, and Max is tuned for slower overnight runs.

CopilotKit released A2UI v0.9 for declarative generative UI, where agents emit JSON and frontends render from a component catalog. The update adds AG-UI support, live incremental rendering, and a shared web core across React, Angular, Flutter, and Lit.

LangChain launched Deep Agents Deploy in beta as a production path for open, model-agnostic agent harnesses configured with AGENTS.md, skills, and mcp.json. Deployments run on LangSmith and can expose MCP, A2A, and agent protocol while teams choose models and sandbox providers.

OpenClaw 2026.3.28 exposes messaging and event handling as nine MCP tools, adds Responses API support, and lets plugins request permission during browser use. Use it to separate transport from agent logic so Claude Code, Codex, Cursor, and local harnesses can share the same account with less glue.

Composio shipped Universal CLI as a shell-first interface to its integrations, moving install, search, and agent workflows out of MCP setup. The release targets users who want simpler agent tool access after complaints that MCP stacks are harder to install, slower, and less stable.

OpenAI rolled out Codex plugins across the app, CLI, and IDE extensions, with app auth, reusable skills, and optional MCP servers. Teams should test plugin-backed workflows and permission models before broad rollout.

Claude Code 2.1.85 adds hook if filters, new MCP header env vars, transcript timestamps, and fixes for /compact overflow, remote leaks, auth flow, and terminal bugs. Upgrade if your workflow depends on hooks or long sessions, and use the new cloud auto-fix flow for unattended PR cleanup.

Rork added Max Publishing to generate icons, screenshots, listing text, review metadata, and submission steps for App Store releases, and also shipped an App Store MCP. Use it first on non-critical apps and keep a manual review gate.

OpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.

CopilotKit shipped hooks that let agents inspect app state and call frontend actions, then paired them with Shadify for ShadCN-based UI composition. It gives embedded agents a cleaner path from chat to in-app behavior.

Claude Code can now run scheduled cloud tasks against remote repos and MCP-connected tools, while Anthropic is also pushing reusable agent SDK and skill controls. Test remote automation paths carefully, because messaging and multi-repo edge cases still surface in practice.

OpenClaw 3.13 now connects to a real Chrome 146 session over MCP so agents can drive your signed-in browser instead of a separate bot context. Update if captchas or auth state were blocking your web automation flows.

OpenCode can now run from AWS CloudShell via npx and inherit AWS auth plus Bedrock models; the same update also brought Firecrawl, India billing, and heap-snapshot debugging. It is becoming a real ops workflow, not just a local terminal toy.

CopilotKit published a generative-ui repo plus an MCP server for bringing agent-built interfaces into existing applications. It gives teams concrete patterns for controlled, declarative, and open-ended UI surfaces instead of ad hoc demos.

Anthropic shipped Claude Code 2.1.80 with research-preview Channels for Telegram and Discord, memory verification before reuse, and fixes for missing parallel tool results on resume. Upgrade if you rely on long-running sessions, SQL analysis, or remote control from chat apps.

Google open-sourced a Colab MCP server that exposes code execution, connection, and notebook editing to MCP-compatible agents. It gives local coding agents a direct bridge to cloud GPUs without hand-rolled notebook automation.

ACE open-sourced ace-platform so teams can self-host its playbook-based context engineering workflow instead of relying only on the hosted service. Use it if you want MCP-compatible prompting infrastructure with your own Postgres, Redis, and deployment controls.

Chrome DevTools MCP now lets agents attach to an existing signed-in browser session, and companion tools added one-command auto-connect flows. Use it to debug and automate in the tabs you already use instead of setting up separate logins or headless sessions.

Emdash v0.4.33 adds open PR review presets, in-app changelog alerts, an expandable mini terminal, and more app handoff targets. Use it to tighten review loops across GitHub, local terminals, and agent sessions.

Claude Code 2.1.75 and 2.1.76 added MCP elicitation dialogs, max effort mode, remote-control session spawning, transcript disablement, and compaction hooks. Teams running longer autonomous sessions get tighter control over inputs, session management, and failure handling.

OpenClaw beta added live control of a real Chrome session through Chrome DevTools MCP; the project also added native SGLang provider support and parallel tool calling work. Try it if you need self-hosted agents to handle authenticated browser flows with local inference backends.

Nous Research shipped Hermes Agent v0.2.0 after 216 merged PRs, adding native MCP support, editor integrations, worktree isolation, rollback, and a larger skills ecosystem. Try it in real repos if you want broader tool support, official Claude support, and lighter installs.

CopilotKit added AG-UI and A2UI support so agents defined with open specs can stream interactive UI directly to the frontend. Use it to reduce custom glue between backend agent runtimes and user-facing interfaces across stacks.