Results for "MCP security"

• Article

  Claimed, Not Enforced: The MCP Security Gap

  From broken authorization to skipped confirmations, Metano’s MCP research found one recurring problem: the control isn’t where the action happens.

  August 31, 2026
• Article

  Metano Integrates with Okta

  Metano is live on the Okta Integration Network. Tie every AI agent to its Okta identity, see what it does at runtime, and stop the agent and its access in one s…

  September 22, 2026
• Article

  Shadow AI Visibility

  Shadow AI starts with visibility, but securing it means understanding what agents actually do.

  August 20, 2026
• Article

  Why Your SIEM Has No Idea What Your AI Agents Did

  Your security stack logs almost everything. The one thing it cannot reconstruct is the decision an agent made, and why it made it.

  July 4, 2026
• Article

  Poetry as a Dead Drop

  Operation Poetic Injustice: your LiteLLM gateway is somebody else’s command-and-control server.

  September 8, 2026
• Article

  Your EDR Can’t See Agent Attacks

  Agents are being weaponized and hijacked, and the orchestration that makes them dangerous is invisible to the telemetry your SOC runs on.

  June 12, 2026
• Article

  Skills Lie. We Stop That.

  A skill’s description is a promise to your agent. Its behavior is the part nobody checks. Every other scanner reads what a skill says it does. SkillTracer runs …

  June 26, 2026
• Page

  Glossary

  Plain definitions for AI agent security: shadow AI, runtime guardrails, agent bill of materials, MCP server, kill switch, non-human identity, and more.

• Page

  Product Overview

  One platform for AI agent security: find every agent and MCP server you run, get runtime guardrails written from each agent’s spec, and enforce inline.