New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

zero_trust

Zero-trust: WireGuard VPN, peer management, mTLS certificates, microsegmentation

SERVERDefense SOURCEdefense-mcp-server
High RISK CLASS
Category Execute
Parameters 121 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/defense/zero-trust.md

What zero_trust does on Defense

AI agents invoke zero_trust to trigger actions in Defense. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

ParameterTypeRequiredDescription
action string Yes Zero-trust networking action
dryRun boolean Preview only
address string Interface address with CIDR e.g. 10.0.0.1/24
denyAll boolean Add deny-all rule for other ports
service string Service name e.g. nginx, postgres
clientCN string Client common name
endpoint string Peer endpoint ip:port
serverCN string Server common name
outputDir string Directory to write certificates
publicKey string Peer public key
validDays number Certificate validity in days
allowPorts array Ports to allow

Parameters from the server's own tool schema.

Why zero_trust is rated High

The zero_trust tool configures network security infrastructure including VPN tunnels, peer management, mTLS certificate issuance, and microsegmentation policies. These operations actively modify network configurations, create/manage cryptographic certificates, and enforce access control boundaries.

From the tool's definition WireGuard VPN, peer management, mTLS certificates, microsegmentation

Risk signalsAccepts URL/endpoint input (endpoint) · High parameter count (18 properties)

Questions about zero_trust

What does the zero_trust tool do? +

Zero-trust: WireGuard VPN, peer management, mTLS certificates, microsegmentation. It is categorised as a Execute tool in the Defense MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does zero_trust accept? +

zero_trust accepts 12 parameters: action, dryRun, address, denyAll, service, clientCN, endpoint, serverCN, outputDir, publicKey, validDays, allowPorts. Required: action. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on zero_trust? +

Register the Defense MCP server in PolicyLayer and add a rule for zero_trust: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Defense. Nothing to install.

What risk level is zero_trust? +

zero_trust is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit zero_trust? +

Yes. Add a rate_limit block to the zero_trust rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block zero_trust completely? +

Set action: deny in the PolicyLayer policy for zero_trust. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides zero_trust? +

zero_trust is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Defense, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Defense's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.