Protect Mcp Setup
wshobson/agentsEvery time an AI agent runs a tool, you need to know it is safe and recorded. This skill adds a policy check before each command. It also creates a signed receipt after every action. Cedar policies decide what the agent can do. If a command is not allowed, it is blocked right away.
Signed receipts record each decision. They include the command, the result, and the policy that was used. Anyone can check these receipts later with a simple tool. No server or account is needed. This makes the whole process easy to verify.
Setting up is simple. You install a plugin and add a few settings. Then every tool call is protected. This is useful for projects that need a clear audit trail, like in finance or healthcare.
Add Protect Mcp Setup skill to your workflow
Global
mkdir -p ~/.claude/skills/protect-mcp-setupProject
mkdir -p .claude/skills/protect-mcp-setupSource Repository
More Security Claude Code Skills
Azure Compliancemicrosoft/azure-skills
Audit Azure compliance and Key Vault expiration with azqr scans
Firebase Security Rules Auditorfirebase/agent-skills
Find weak spots in Firestore rules and get clear fixes
Golang Securitysamber/cc-skills-golang
Find and fix security flaws in Go code using expert guidance and automated tools
Clerk Nextjs Patternsclerk/skills
Secure your Next.js app with Clerk middleware, server actions, and caching
Persona It Admingoogleworkspace/cli
Keep your digital workspace safe with IT admin security workflows
Two Factor Authentication Best Practicesbetter-auth/skills
Secure user logins with two-factor authentication using Better Auth
Gws Modelarmor Create Templategoogleworkspace/cli
Create new templates for Google Model Armor to protect AI apps from harmful content
Gws Modelarmor Sanitize Promptgoogleworkspace/cli
Clean user prompts safely with Google Model Armor templates