MCP

OpenRouter released an MCP server that lets agents query live model pricing, benchmark scores, provider data, docs, and run test inference from the CLI. That replaces stale model knowledge with current routing data inside long-running agent workflows.

Latitude released an open-source platform for monitoring AI agents in production, with plain-English trace search, repeated-failure clustering, and MCP access from coding agents. That gives teams a self-hostable way to inspect token burn, surface recurring failures, and turn production traces into evals and fixes.

Claude Code 2.1.187 adds sandbox.credentials to block credential and secret-env access from sandboxed commands and aborts remote MCP calls after five minutes. It also adds org model restrictions and fixes structured-output retry loops.

Claude Code 2.1.186 adds CLI-based MCP auth, automatic assistant replies after ! shell commands, and tighter named-subagent permission checks. The update cuts interactive setup for remote MCP servers and tightens policy-heavy agent workflows.

Anthropic introduced an MCP extension that lets admins authorize connectors through their identity provider instead of repeated per-user OAuth flows. VS Code added support the same day, which matters because teams can keep connector policy and audit controls in existing enterprise identity systems while reducing setup friction.

Epic added experimental MCP server support in Unreal Engine 5.8 so compatible agents can inspect the engine and active project inside Unreal Editor. Hermes Agent added the server to its MCP catalog the same day, which matters because it lowers setup friction for agent-driven game-development workflows.

Firecrawl released a research-specific search index with 3M+ arXiv papers, GitHub artifacts, and a /search/research interface across API, CLI, MCP, and SDKs. It combines literature retrieval, claim verification, and code lookup in one surface for research agents.

OpenCode v1.17.7 added active-server reuse for plugin clients, workspace roots for MCP servers, and SDK auto-refresh for models and credentials. It follows a 1.17.6 compatibility update that declared OpenCode's supported client capabilities to improve MCP interoperability.

Hyperbrowser shipped a Claude Code harness, InsForge showed a Fable run drop from 5.5M to 2.3M tokens, and Higgsfield published new MCP workflows. These tools add reusable harness, context, and interface layers around Fable for more controlled runs.

Files SDK 1.8 shipped cross-adapter search plus typed plugins for compression, encryption, dedup, tracing, usage metering, validation, and versioning. Use it to compose storage hooks and power CLI and MCP search flows.

Repo Prompt Community Edition went live on GitHub as an open-source orchestration app built around MCP-first agent control, while the legacy project was archived separately. It matters because builders now get a public harness that can swap underlying CLI agents without rewriting the control surface.

TanStack AI added MCP support for single or multiple servers, standalone clients or pooled servers, and a CLI for type generation. The release gives app builders a typed integration path for MCP-managed tools inside chat and agent workflows.

Independent developers shipped sidecars that let Claude Code, Cursor, and Codex share memory, hot-swap model providers, package local projects as apps, and automate browser QA. Try these reusable tools if you want memory, routing, QA automation, and app packaging outside editor-specific features.

Hermes Agent shipped Tool Search, which loads tools on demand when MCPs or plugins would otherwise consume a large chunk of context. The feature targets lower token use and less prompt clutter in large tool catalogs.

Nous Research released Hermes Agent v0.15.0 with skill bundles, MCP Catalog, new model support, and major performance and security work. The update cuts load times 50%, speeds session search 750x, and adds Bitwarden plus prompt-injection defenses.

OpenAI said ChatGPT, Codex, and the Responses API can reach private MCP servers over outbound-only HTTPS without inbound exposure. The same enterprise update adds workload identity federation plus admin controls for spend alerts, allowlists, retention, and hosted tools.

Hermes Agent added a built-in MCP Catalog while separate builders shipped Qwen3.7 Max support, Venice private-model workflows, and Krea 2 image generation. The cluster shows Hermes moving beyond a single-model assistant toward a broader agent shell with tool, model, and media providers.

Claude Code 2.1.153 adds skipLfs for Git and GitHub clones and fixes a stateful MCP regression introduced in v2.1.147. The release also stops custom gateways from receiving a user's Anthropic OAuth credential and pairs with broader responsiveness work.

Cua Driver said its Windows backend is now stable, letting Claude Code, Codex, Hermes, or custom agents drive real Windows apps through MCP or CLI. The release targets Windows-only line-of-business software while keeping the desktop usable with multi-pointer support.

Weights & Biases released an MCP server that exposes experiment data to Claude Code, Cursor, Codex, Gemini CLI, and Le Chat. The schema-first design helps agents inspect available metrics before pulling rows, which can prevent preview runs from overflowing context windows.

A new MeMo paper and several community memory systems converged on keeping knowledge outside the base model through recipe files, semantic and autobiographical stores, and background reconsolidation. The pattern matters because engineers are treating context loss as a systems problem instead of only asking for larger context windows.

Independent developers released browser-control MCP tooling, repo-context graphing and packaging utilities, and token-compression helpers for coding agents. The cluster matters because agent workflows are now adding browser control, context packing, and cost controls as external infrastructure instead of waiting on raw model upgrades alone.

TimescaleDB added a read-only MCP mode, practitioners pushed credential brokering, and an OpenClaw user open-sourced a skill-quarantine review pipeline. That matters because secret handling and destructive permissions are moving out of prompts and into brokered or reviewable control layers.

New guides, plugins, and reusable libraries show the Agent Skills format moving beyond Claude Code into multiple coding-agent clients and runtimes. That matters because workflows are becoming portable artifacts instead of one-off prompts tied to a single harness.

The MCP 2026-07-28 release candidate makes the protocol stateless, removing the handshake and session ID. That changes how MCP servers can be load-balanced, retried, and deployed behind standard infrastructure.

Anthropic added self-hosted sandboxes in public beta and MCP tunnels in research preview to Claude Managed Agents. Use the new options to keep agent execution inside your perimeter or private cloud and reach internal MCP servers without public exposure.

Google introduced WebMCP as a proposed bridge between websites and coding agents, and paired it with Chrome DevTools support for agent debugging plus Modern Web Guidance. It matters because Google is trying to standardize browser-facing agent behavior, not just model APIs.

Anthropic said it is acquiring Stainless, the SDK and MCP server platform behind Anthropic’s own official SDKs across major languages. The deal matters because Anthropic is bringing a key part of its API and agent-connectivity toolchain in-house while developers reassess alternative codegen stacks.

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.

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.

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.

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.

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.

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.

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.

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.