GitLab 19.5: MCP Server GA Lets Outside Agents In, With Limits
GitLab 19.5 makes its MCP server generally available, governs Claude Code and Cursor sessions, and adds rate limits. What platform teams should configure first.
Octopus Deploy Remote MCP: Agents Can Now Ship Releases
Octopus Deploy remote MCP lets AI agents deploy releases and run runbooks through a built-in /mcp endpoint. What it exposes, and the guardrails to set first.
Datadog BYOC Cross-Cluster Queries: One Search, Data Stays Put
Datadog BYOC Logs can now search several self-hosted clusters in one query, including for AI agents via MCP. What that fixes for data-residency observability.
One MCP Server Burned 18,000 Tokens Before Your Agent Did Anything. Here's the Fix.
One MCP server burned 9% of a 200K context window at initialization. Pi's Codemode pattern cuts that overhead to under 2% — and applies beyond Pi.
The Closed-Loop Incident Response Pattern: How AWS DevOps Agent Uses OpenSearch MCP to Investigate Itself
OpenSearch alerts can hand AWS DevOps Agent the same observability data via MCP, taking incidents from SNS trigger to root cause analysis in five minutes.
Datadog's MCP Server Now Runs Code — and Cuts AI Agent Investigation Costs 73% in the Process
Datadog's MCP Server now runs sandboxed JavaScript for AI agents, cutting input tokens 73% and lifting answer correctness from 74% to 90% across 25 tasks.
MCP Went Stateless: The AWS Well-Architected Audit Your MCP Server Needs Now
MCP's July 28 protocol update eliminated session state — and with it, the sticky load balancers, DynamoDB session stores, and Lambda workarounds most AWS MCP deployments were built around.
Anthropic's Model Hardware Standard: MCP Arrives in the Physical World
Anthropic's MHS extends MCP to lab hardware, cutting device integration from weeks to hours. Early Carnegie Mellon tests hit 99.3% success — with one significant caveat.
Building Production Agentic AI: What IBM Learned the Hard Way
IBM deployed a multi-agent platform with LangGraph and MCP in months. Three hard lessons: instrument early, baseline before build, and solve data access first.
MCP vs API: CircleCI's Practical Guide to When Each Makes Sense
CircleCI's engineering blog clarifies the actual distinction between APIs and MCP — and why the answer for most agentic systems is 'both, for different purposes.'
How AgentFlo Built WhatsApp Commerce Agents on Amazon Bedrock AgentCore
AgentFlo's WhatsApp commerce agents serve merchants processing $300B in annual volume — here's the Bedrock AgentCore architecture enabling multi-tenant AI sales at scale.
How to Bring Organizational Knowledge Into Kiro Using Amazon Bedrock and MCP
AWS shows how to connect Kiro to Amazon Bedrock Knowledge Bases via MCP so developers get instant, cited answers about ADRs, API specs, and coding standards without leaving their editor.
Agent Protocol: The Open Standard for AI Plugin Packaging
Amazon, Cursor, Microsoft, OpenAI, and Vercel released Agent Protocol — a unified spec for AI agent plugin packaging that ends the per-platform rebuild cycle.
AWS IaC MCP Server: What CloudFormation Development Looks Like with Unified AI Tooling
AWS's IaC MCP Server consolidates CloudFormation documentation search, syntax validation, compliance checking, and runtime troubleshooting into one conversational interface. Here's what that workflow change actually delivers.
LLM 0.32: Simon Willison's CLI Now Surfaces Model Reasoning and Connects to MCP Servers
LLM 0.32 adds visible reasoning traces, server-side tools for OpenAI and Anthropic, OpenAI Responses API compatibility, and a Git-like content-addressable log. Here's what changed and why it matters for agentic workflows.
Stateless MCP: Why the Protocol Dropped Session IDs
The 2026-07-28 MCP spec update replaced two-request session handshakes with a single stateless call — simplifying how agentic tools scale.
JFrog's Agent Guard Targets the MCP Servers Nobody in Security Approved
36% of MCP servers and agent skills tested carry a security flaw. JFrog's Agent Guard adds an approved-only proxy so developers can't connect coding agents to ungoverned tools.
How to Add a Custom MCP Server to Claude and ChatGPT
A step-by-step look at connecting a custom MCP server to Claude and ChatGPT's chat interfaces — and where ChatGPT's setup gets far more involved.
AWS DevOps Agent + Wiz: Same Alert, Three Different Incidents
AWS DevOps Agent now queries Wiz over MCP mid-investigation, turning an ambiguous CPU spike into a confirmed security incident, an operational fix, or a coverage gap.
Pilot Protocol Wants to Be the Network Layer AI Agents Never Had
Pilot Protocol launched a UDP-level networking stack for AI agents — with 219,000 agents already running, native wallets, and no API keys required.
Remote MCP Servers: Why 'Just Run It Locally' Stopped Working
Remote MCP servers move tool access from a developer's laptop to hosted infrastructure — here's the architecture shift and why CircleCI built one for CI/CD.
Platform Engineering's Next Job: Managing AI Agents Like Any Other Workload
CNCF's case for the agentic enterprise: platforms must treat AI agents as first-class citizens alongside applications and resources, with shared context as the new primitive.
Datadog's MCP Security Agents: What Production Looks Like Beyond the Demo
Datadog built MCP tools for Cloud SIEM operations and published the engineering decisions. Progressive disclosure cut token usage 41%. Here's the architecture.
AI Agents Now Have a Package Manager — and JFrog Is the Enterprise Registry
APM (Agent Package Manager) treats agent primitives like versioned software packages. JFrog's Artifactory adds native support, bringing supply-chain governance to AI agent configuration.
CircleCI Rewrote Its CLI in Go Because Coding Agents Needed Predictability
CircleCI's CLI rewrite isn't a developer ergonomics play—it's infrastructure for agentic CI/CD. Consistent JSON, stable exit codes, and a first-class MCP server are now the requirements.
Gemini API Adds MCP and Background Execution: What Changes for Agent Builders
Google Deepmind's Gemini API Managed Agents now support background execution and remote MCP server connections—removing the two most common blockers for production agent deployment.
Why Uniform AI Agent Governance Fails — and What to Do Instead
Gartner projects 40% of enterprises will demote or decommission AI agents by 2027 due to governance failures. JFrog's analysis of why one-size-fits-all governance breaks down, and the tiered alternative.
AWS Agent Toolkit: Why Your Agent Is Ignoring 20+ Skills Without This One File
AWS launched an Agent Toolkit with 20+ packaged skills for coding agents, but most developers miss the rules file that tells agents to use them — causing silent fallback to training data instead of authoritative AWS guidance.
Amazon Launches Web Search API for AI Agents Inside AWS: $7/1K Queries, Zero Data Egress
AgentCore Web Search gives AI agents access to current web knowledge via Amazon's search infrastructure — $7 per 1,000 queries, queries never leave AWS, returns snippets and publication dates, MCP connector via AgentCore Gateway. GA in US East as of June 17, 2026.
Agentjacking: How a Public Sentry Key Hijacks Claude Code, Cursor, and Codex
A newly documented attack called agentjacking exploits Sentry's MCP integration to inject fake bug reports into AI coding agents, which then execute malicious commands with developer-level privileges.
AWS DevOps Agent + LaunchDarkly: Feature Flags as Incident Response
AWS DevOps Agent now connects to LaunchDarkly's MCP server, enabling agentic feature flag orchestration at deployment and during incidents — flag-based containment in minutes, not rollbacks.
AWS DevOps Agent and Datadog MCP Server Are Both Generally Available — Here's What Changed
Both tools exit preview simultaneously: DevOps Agent now coordinates with Slack, PagerDuty, and ServiceNow; Datadog's MCP Server routes AI agent prompts to live observability data. Together they close the detection-to-prevention loop.
AWS Summit New York 2026: What Actually Matters for Platform Engineers
AWS Summit New York 2026 delivered 15+ announcements. Here's what platform engineers should pay attention to: autonomous agents going GA, ECS 4.2x faster scaling, and the agentic CI/CD stack taking shape.
MCP's Missing Enterprise Authorization Layer Is Now Filled
The Enterprise-Managed Authorization extension for the Model Context Protocol eliminates per-server OAuth consent prompts, letting IT admins provision MCP server access centrally through existing identity providers.
Datadog MCP Apps Bring Rendered Dashboards Into Claude, Cursor, and ChatGPT
Datadog's MCP Apps extend the Model Context Protocol with rendered UI components — interactive monitor cards, timeseries graphs, and APM trace views — surfaced directly inside AI coding and chat interfaces.
AWS Extends Its DevOps Agent to Diagnose EKS Node Issues via Custom MCP
A custom MCP server bridges AWS DevOps Agent to SSM Automation runbooks, giving the agent structured access to 20+ OS-level log sources — and it completed an autonomous DNS root-cause analysis in 14 minutes.
JFrog Brings Xray Security Data Into Amazon Kiro With a New Open-Source Power
JFrog Power for Kiro adds artifact search, repository management, and live CVE data from JFrog Xray directly into Kiro's MCP-native IDE — closing the gap between AI-assisted coding and security validation.
agentgateway Joins AAIF: The MCP Router With 300+ Contributors Gets a Linux Foundation Home
agentgateway—the open-source gateway for MCP, agent-to-agent protocols, LLM inference, REST, and gRPC—joins the Agentic AI Foundation as its fourth hosted project, bringing enterprise governance and observability to agentic traffic.
JFrog's Claude Code Plugin Puts Supply Chain Security Where AI Decisions Happen
JFrog embeds dependency validation, MCP server governance, and Artifactory access directly into Claude Code—shifting supply chain security left into the agentic development loop.
JFrog's MCP Integration: Ask Your Platform to Provision Itself
JFrog's new MCP server lets AI coding agents like Cursor and Claude Code provision Artifactory repos, run Xray security scans, and trace release bundles — in plain language, without navigating dozens of UI screens.
Amp CLI: Multi-Agent Orchestration for Solo and Team Developers
Amp's Neo CLI rebuild brings sub-agent orchestration and persistent project memory to agentic developer workflows — how it compares to Claude Code and Cursor.
GitHub MCP: The Immune System AI Coding Agents Were Missing
GitHub's MCP Server now scans for secrets and vulnerable dependencies before commits — closing the security gaps that AI-assisted coding creates at scale.
AWS MCP Server: IAM-Native Access to 15,000+ AWS APIs
AWS's official MCP server covers 15,000+ APIs through one tool with IAM-native auth. Free, agent-agnostic, and available for Claude Code, Cursor, and Kiro.
JFrog MCP Registry: Governing AI Agents at the Tool Level
JFrog MCP Registry enforces AI agent permissions at tool level, not server level — giving Google Cloud teams governed self-serve MCP access without accepting blind security risk.
AWS Bedrock Is an MCP Spec Maintainer. Here's What That Means for the Protocol.
AWS Bedrock team member Luca Chang maintains the MCP specification — contributing Tasks and Elicitations features driven by cloud platform use cases. The hyperscaler's seat at the table shapes the protocol's enterprise trajectory.
JFrog Skills: Open-Source Toolkit for AI Agents That Understand Software Supply Chains
JFrog's open-source Platform Skills library lets AI agents query CVE data, verify artifact provenance, and enforce governance policies using natural language — with MCP support for Cursor and Claude Code.
Amazon Is Betting Big on MCP — and That Changes What the Standard Becomes
AWS isn't just supporting the Model Context Protocol — it's shaping the spec from inside. What AWS builds into MCP determines what every enterprise AI agent stack will look like.
Datadog Code Security MCP: Security Scanning Inside AI Code Generation
Datadog launched an MCP server that runs SAST, SCA, secrets detection, and IaC scanning during AI code generation — catching vulnerabilities before they reach a pull request.
MCP Enterprise Security Roadmap: What Four Major AI Vendors Agreed On
Anthropic, AWS, Microsoft, and OpenAI aligned on four enterprise MCP priorities at the April 2026 Dev Summit. Here's what the roadmap means for teams deploying AI agents at scale.
pgEdge: Why AI Agents Should Use MCP, Not REST, for Postgres
pgEdge launched an MCP server for Postgres that cuts token usage 30-50% versus REST APIs — and it works with Claude Code, Cursor, and Windsurf out of the box.