// SCAN REPORT

Defense

31 tools. 27 can modify or destroy data without limits.

27 write tools that can modify data. Rate limits recommended.

Last updated: 5 Aug 2026

27 can modify or destroy data

4 read-only

31 tools total

Community server · catalogue entry checked 05/08/2026 · full schemas captured for 31 of 31 tools

How to control Defense ↓

TOOL MAP

What Defense exposes to your agents

Read (4) Write / Execute (27) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Defense costs in tokens

11,976 tokens of tool definitions, loaded on every request

6.0% of a 200k context window

922 heaviest tool: log_management

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Defense tools

Execute · Critical sudo_session This tool manages sudo privilege elevation, which allows executing commands with root/superuser permissions. Execute · High crypto This tool executes cryptographic operations and audits across multiple subsystems. Execute · High ebpf eBPF (extended Berkeley Packet Filter) and Falco rule deployment constitute code execution on the kernel/system level. Execute · High malware This tool performs active operations including scanning filesystems, updating AV definitions, applying YARA rules to detect malware, and quarantining files.

27 of Defense's 31 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Defense

PolicyLayer is an MCP gateway — it sits between your AI agents and Defense, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "access_control": {
    "limits": [
      {
        "counter": "access_control_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "api_security": {
    "limits": [
      {
        "counter": "api_security_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Defense — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DEFENSE →

Instant setup, no code required.

FULL CATALOGUE

All 31 Defense tools

EXECUTE 14 tools

Execute app_harden App hardening: audit running apps, recommendations, firewall rules, systemd sandboxing Execute container_isolation Container isolation: AppArmor, SELinux, namespaces, seccomp, rootless setup Execute crypto Crypto: TLS/SSL audit, GPG, LUKS, file hashing, certificate lifecycle Execute ebpf eBPF/Falco: list eBPF programs, Falco status, deploy rules, read events Execute firewall Firewall: iptables, UFW, nftables, persistence, policy audit Execute harden_kernel Kernel hardening: sysctl, kernel security, bootloader, memory protections Execute honeypot_manage Deception: canary tokens, honeyport listeners, trigger detection, canary management Execute incident_response Incident response: volatile data, IOC scan, timeline, forensics (memory/disk/network/evidence/custody) Execute malware Malware: ClamAV scan/update, YARA rules, suspicious files, webshells, quarantine Execute sudo_session Sudo: elevate privileges, check/drop/extend session, preflight tool checks Execute vuln_manage Vulnerabilities: nmap scan, nikto web scan, tracking, risk prioritization, remediation plans Execute waf_manage WAF: ModSecurity audit, rule management, rate limiting, OWASP CRS, blocked request analysis Execute wireless_security Wireless: Bluetooth audit, WiFi assessment, rogue AP detection, disable unused interfaces Execute zero_trust Zero-trust: WireGuard VPN, peer management, mTLS certificates, microsegmentation

WRITE 13 tools

Write access_control Access control: SSH, PAM, sudo, user audit, password policy, shell restriction Write backup Backup: config files, system state snapshots, restore, verify integrity, list backups Write compliance Compliance: Lynis, OpenSCAP, CIS benchmarks, framework checks, policy, cron/tmp hardening Write container_docker Docker security: audit, CIS bench, seccomp, daemon config, image scan Write defense_mgmt Defense: tool checks, workflows, change history, posture, scheduled audits, remediation, reports Write harden_host Host hardening: services, permissions, systemd, cron, umask, banners, USB control Write integrity Integrity: AIDE, rootkit scanning, file hashing, drift baselines Write log_management Logging: auditd, journalctl, fail2ban, syslog, log rotation, SIEM integration Write network_defense Network: connections, traffic capture, port scan detection, IPv6 audit, self-scan, segmentation Write patch Patches: pending updates, unattended upgrades, package integrity, kernel audit, CVE lookup Write process_security Processes: audit running, capabilities, namespaces, anomaly detection, cgroup limits Write supply_chain Supply chain: SBOM generation, cosign artifact signing, SLSA provenance verification Write threat_intel Threat intel: IP/hash/domain reputation, feed management, blocklist application

READ 4 tools

Read api_security API security: local API discovery, auth audit, rate limiting, TLS verify, CORS check Read cloud_security Cloud: environment detection, metadata audit, IAM credentials, storage audit, IMDS security Read dns_security DNS: resolver audit, DNSSEC check, tunneling detection, domain blocklists, query log audit Read secrets Secrets: filesystem scan, env variable audit, SSH key sprawl, git history leak detection

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Defense

How do I prevent bulk modifications through Defense? +

The Defense server has 13 write tools including access_control, backup, compliance. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Defense.

How many tools does the Defense MCP server expose? +

31 tools across 4 categories: Destructive, Execute, Read, Write. 4 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on Defense? +

Register the Defense MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Defense tool call.

Deterministic rules across all 31 Defense tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEFENSE →

Instant setup, no code required.

31 Defense tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Defense's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

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