AI
How to find MCP servers in your codebase and clusters
Find MCP servers in repos with .mcp.json and claude mcp list, then in clusters by listing pods and images. Covers scopes, approvals and shadow servers.
6 min read
Tag
AI Governance
10 posts
AI
How to audit MCP tool calls
Audit MCP tool calls in Claude Code with OpenTelemetry tool events and OTEL_LOG_TOOL_DETAILS=1, plus hooks that record each server's source and denied calls.
6 min read
AI
Claude Code managed settings for enterprises
Claude Code managed settings sit above every developer file. Deploy managed-settings.json per OS or through MDM, check it with /status, then lock the rules.
7 min read
AI
How to route Claude Code through an AI gateway
Point Claude Code at an AI gateway with ANTHROPIC_BASE_URL and a gateway credential, verify it with curl and /status, then roll it out with managed settings.
6 min read
AI
How to control MCP servers in GitHub Copilot
Control MCP servers in GitHub Copilot with the MCP policy, registry-only mode, managed-settings allowlists and cloud agent settings. See where each one applies.
5 min read
AI
How to restrict which MCP servers Claude Code can use
Restrict Claude Code MCP servers with managed-mcp.json, allowedMcpServers and deniedMcpServers. Learn the match rules, the deny-first order and the gaps.
6 min read
AI
How to block destructive commands in Claude Code
Block rm -rf and other destructive Claude Code commands with Bash deny rules, a PreToolUse hook and managed settings. Learn where each layer stops and fails.
5 min read
AI
Who Controls Your AI Agents? Jim Bugwadia on Policy as Code for AI Governance
Jim Bugwadia explains how to govern AI agents with policy as code: decouple rules from apps, enforce every LLM, MCP and agent call, and keep developers moving.
4 min read
Kubernetes
Introducing OttoFlow: AI Workflows for Kubernetes
AI workflows for Kubernetes, without handing an agent your kubeconfig. OttoFlow makes a workflow a custom resource: typed DAG steps, AI only where it counts.
6 min read
AI
Introducing Nirmata Runtime for Kyverno: Kernel-Level Enforcement for AI Workloads
Nirmata created Kyverno and donated it to the CNCF in 2020. Kyverno is now a graduated CNCF project and is widely used for enforcing and automating configuration security…
7 min read