Model Context Protocol

Straiker, an agentic AI security company, announced on October 9, 2026 that it was named "Cybersecurity Solution of the Year for Artificial Intelligence" in the 2026 CyberSecurity Breakthrough Awards. Its platform has three capabilities: Discover AI for visibility into AI agents, MCP servers, Agent Skills, tools, and connections; Ascend AI for autonomous adversarial testing of prompt injection, tool misuse, and data exfiltration; and Defend AI for real-time runtime protection with an agentic kill switch to contain compromised agents.

Endor Labs and SpaceXAI are partnering to secure agentic software delivery on Grok Build, from the first tool call to merged pull requests. Endor Labs checks code and dependencies as agents produce them and fixes issues before they leave the session. The integration started with a free MCP server, added a hooks integration in December 2025 that scans every package an agent installs, added Coding Agent Governance in May 2026, and added the Endor Labs Agent Kit in June.

Gartner's Emerging Tech Impact Radar: AI Cybersecurity Ecosystem lists Straiker as a Sample Vendor in two categories: AI Security Testing and AI Security Platforms. Straiker says these reflect a shift toward continuously attacking AI systems to find weaknesses and using those findings to protect them in production. The source ties this to agentic AI, where testing must cover MCP servers, tools, and database access, not only model prompts.

AI agents are spreading into enterprises faster than many security programs were built to handle. They read email, access SaaS applications, query databases, invoke APIs, use MCP tools and modify records. The source text is cut off before it describes any specific controls.

Check Point has released the Workforce AI MCP, its own Model Context Protocol server for Workforce AI Security. Connecting a compatible AI client lets administrators query, analyze and manage employee AI usage policy in natural language rather than through filters, screens and individual rule checks. The server covers users, managed assets, GenAI application usage, DLP data types, and agent and MCP activity within a single conversation.

Google is opening its smart home platform to third-party AI agents through a new Google Home MCP integration. The integration lets agents that support the Model Context Protocol, including Claude and Open Claw, control and monitor connected devices and access event history.

AIR Security has emerged from stealth with $50 million in funding, led by Sequoia Capital and Greenoaks, for a firewall that protects AI agents. Its research found more than 17,800 public AI add-ons (6.7M installations) relying on untrusted external instruction sources, and AI Skills impersonating Anthropic and OpenAI. The firewall screens skills, plugins, MCP servers and add-ons before and after deployment and can revoke them organization-wide.

AI security startup AIR has come out of stealth with $50 million raised across two seed rounds, led by Sequoia and Greenoaks, to build a product that monitors the supply chain of skills, plug-ins, MCP servers and add-ons used by AI agents. The platform discovers agents running in a company, vets their tools against a whitelist AIR maintains, and blocks those that fail security criteria. AIR says its platform currently filters out about 27% of the add-ons and skills it finds online.

CrowdStrike is introducing Falcon Guardian, the evolution of Falcon AI Detection and Response (AIDR), to secure AI agents at runtime on Windows, macOS and Linux endpoints. The product discovers known and unknown agents and fuses their prompts, tool calls and MCP server use with endpoint telemetry to link prompts to downstream system actions. It also adds an AI gateway and extends MDR and cross-domain threat hunting to the platform.

Claude Code runs file reads, shell commands and MCP tool calls on developers' machines, where the harness, not the LLM, executes actions and holds the credentials. Anthropic's new Compliance API endpoints give security teams a clearer view of that local activity, but the article argues activity logs alone cannot show whether an agent's access is legitimate. Token Security reports that local agents account for 68.6% of the AI agents it discovers in customer environments.

Amazon Bedrock Guardrails validates model inputs and outputs, but data that flows through tool calls, external data sources and MCP servers sits outside the model boundary. The article proposes three validation checkpoints built with Strands Agents SDK lifecycle hooks and Amazon Bedrock guardrails to extend coverage to those trust boundaries without changing existing tools or agent logic. The first checkpoint, inbound data validation, uses a BeforeInvocationEvent hook to block policy-violating content before it reaches the model.

MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams know the server is running. The MCP server sits between an AI agent and enterprise systems, so it typically holds credentials such as service account keys, API tokens and other secrets for every system it touches.