MCP
30 days · UTC
Synchronizing with global intelligence nodes...
OpenAI Batch API outage exposes brittle AI ops and governance gaps
OpenAI’s Batch API outage broke file-backed jobs and highlighted how fragile many AI-powered pipelines and controls still are. Developers reported th...
Real-time AI DLP moves to the browser and the MCP layer
Nightfall AI now blocks sensitive data at paste-time and monitors MCP agent traffic, shifting DLP from after-the-fact alerts to real-time prevention. ...
GitHub Copilot’s HydraFusion turns model choice into runtime workflows
GitHub Copilot introduced HydraFusion, a research-preview router that builds per-request, multi-model workflows to balance quality, latency, and token...
OpenCode goes protocol-first: MCP tools, LSP code intel, and a Plan/Build agent split
OpenCode now treats coding agents like IDEs: protocol-first, model-agnostic, with MCP tools, LSP code intel, and a Plan/Build split. This [explainer]...
MCP Goes Stateless: Scale Agent Tools Like Any HTTP Service
The Model Context Protocol is now stateless, removing session pinning and letting agent tool backends scale behind ordinary HTTP load balancers. [MCP...
LangChain adds beta MCP adapter; Datasette ships MCP server — agents plug into data with less glue
LangChain now adapts MCP servers into tools while Datasette exposes an MCP server endpoint, tightening the agent-to-data interface. LangChain’s 1.4.0...
claude-mem fixes installer outage, hardens quotas/observer; Claude Code adds governed delivery and MCP server
claude-mem tightened quota and observer behavior and fixed an installer outage, while Claude Code tools added governed delivery and an MCP server. Th...
LangChain ships alpha MCP adapter powered by FastMCP
LangChain released an alpha MCP adapter that turns any MCP server into agent tools you can hand straight to create_agent. The alpha [langchain.mcp](h...
WebMCP turns agent automation into first‑class site actions; make your agent docs testable
WebMCP is moving real agent automation from scraping to site-declared tools, and teams should treat agent-facing docs as testable interfaces. [WebMCP...
MCP tool schemas are eating your context window — here’s how to cut 4–32x token cost
MCP clients load full tool schemas into the model context, causing 4–32x higher token use than CLI-based discovery. A deep-dive shows the default “li...
Agents can now pay for APIs: AWS ships AgentCore Payments GA
AWS made AgentCore Payments generally available, enabling agents to buy access to APIs and content mid-run under spend controls. InfoWorld reports AW...
Mindstone launches an "Agentic AI Academy" focused on supervising real workflows, not prompts
Mindstone is offering a 4‑week Agentic AI Academy that trains teams to direct and supervise agent workflows instead of one‑off prompting. The program...
Grok 4.6 makes long‑running agents cheaper and sturdier
SpaceXAI launched Grok 4.6 with aggressive pricing and persistent memory aimed at long‑running agents. Early reports say Grok 4.6 cut token prices an...
Authenticated AI agents are now a security boundary (MCP and Chrome make it obvious)
Agentic AI with logged-in access is exposing new security gaps across MCP integrations and Chrome’s Auto Browse. Google’s Gemini-powered Auto Browse ...
Claude Code 2.1.228 hardens synced skills and stabilizes runners
Anthropic shipped Claude Code 2.1.228 with concrete security hardening for synced skills and reliability fixes across the CLI and self‑hosted runners....
GitHub Copilot steps into multi-agent development with a desktop app and a cloud agent
GitHub Copilot now runs agent-driven workflows with a desktop app and a cloud agent that can plan work, change code, and open PRs. The new Copilot ap...
Microsoft Foundry ships Tool Search to shrink tool schema costs
Microsoft Foundry introduced Tool Search so agents don’t ship huge tool catalogs every turn, cutting token spend and reducing tool misfires in large s...
Agentic coding grows up: prove it, cap it, then scale it
Agentic coding is shifting from flashy demos to auditable, budgeted workflows teams can trust in production. A cheerleading take on agents like Curso...
MCP goes stateless: scale improves, ops and security get real work
MCP just switched to a stateless core and is aiming for enterprise scale, but ops and security need new guardrails. The new spec makes MCP’s core sta...
Safari MCP brings agents into the browser; routing and cost tooling catch up
Safari’s new MCP server lets agents see and act in a real browser, shifting agent work from code-only to runtime debugging. WebKit’s Safari Technolog...
Agent identity grows up: A2A v1.0 and the push from sandboxes to production
Agent identity for AI agents is moving from talk to something you can actually ship and audit. [A2A v1.0](https://hackernoon.com/the-identity-layer-f...
IDEs are becoming agent orchestrators: Zed and Windsurf make agents first‑class with reviewable flows and MCP hooks
Mainstream editors are shifting from autocomplete to agent orchestration, with Zed and Windsurf shipping native agent workflows and protocol hooks. Z...
claude-mem v13.10.2 hardens agent memory: fewer SQLITE_BUSY, saner workers, better Windows
claude-mem shipped a stability-focused patch that fixes worker identity drift, Windows spawns, and SQLite contention under load. The v13.10.2 release...