k9 Security
  • Use Cases
    • DevOps
    • Enterprise Security
    • MDR & SOC
    • OEM Integrations
  • Demo
  • Pricing
  • Docs
  • Contact
  • About
  • Blog
  • Sign up
Select Page

Your MCP server on AgentCore Runtime fails its health check at `/mcp/`. Here’s how to fix it.

by Stephen Kuenzli | Jun 2, 2026 | Development

We deployed the k9 MCP server to AWS Bedrock AgentCore Runtime. Tool calls worked for the first few minutes of every session, then started failing with MCP error -32010: Runtime health check failed or timed out. Local tests stayed green throughout. The fix is one...

Generate least-privilege EventBridge policies and restrict access to your AWS Organization with k9-cdk

by Stephen Kuenzli | Apr 10, 2026 | Announcements

Cross-account event buses are one of the most powerful integration patterns in AWS, and an easy place to make an access policy mistake. A single overly permissive Allow statement can let principals from outside your organization publish events to your bus. With k9-cdk...

Building Evals for an AI Agent: From Zero to Consistency Testing

by Stephen Kuenzli | Apr 2, 2026 | AI, Security

We’re building an AI agent that triages cloud security findings. It reads a finding from AWS Security Hub or Prowler, assesses the risk, and tells an engineer exactly what to do about it with specific AWS CLI commands they can run. The agent worked. We had 620...

How to Connect Strands Agents to AWS MCP with IAM Authentication

by Stephen Kuenzli | Mar 31, 2026 | AI

We’re building a cloud security agent with Strands Agents that triages AWS security findings. The agent uses the AWS Knowledge MCP server to search and read AWS documentation. The agent looks up remediation guides, CLI syntax, and best practices as part of its...

Export Findings from Security Hub in OCSF Format: A Complete Guide

by Stephen Kuenzli | Oct 1, 2025 | Security

Security teams have long been challenged by security findings scattered across many tools in proprietary formats that don’t play well together. If you’re managing AWS Security Hub findings and need to analyze them alongside data from other security tools,...
« Older Entries

Recent Posts

  • How to Prioritize CVEs by Risk, Not Severity
  • Your MCP server on AgentCore Runtime fails its health check at `/mcp/`. Here’s how to fix it.
  • Severity is no longer a triage input. Risk scoring you own is.
  • Generate least-privilege EventBridge policies and restrict access to your AWS Organization with k9-cdk
  • Building Evals for an AI Agent: From Zero to Consistency Testing

Recent Comments

    Copyright 2026 K9 Security Inc.