# execute_cli_script

A execute tool on the Fortimanager MCP server.

Agent View of the PolicyLayer registry record for `execute_cli_script`. HTML page: https://policylayer.com/tools/jmpijll-fortimanager-mcp/execute-cli-script

## Facts

- Tool: `execute_cli_script`
- Server: Fortimanager (`jmpijll/fortimanager-mcp`) — https://policylayer.com/tools/jmpijll-fortimanager-mcp.md
- Homepage: https://github.com/jmpijll/fortimanager-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "execute_cli_script",
    "arguments": {}
  }
}
```

## Why execute_cli_script is rated High

This tool runs scripts via CLI against a FortiManager system. Even with an empty description, the name and context make clear this executes arbitrary commands whose effects depend entirely on the script content provided by the caller. This is Execute category: triggering external operations (CLI scripts on security infrastructure) whose side effects are determined by arguments.

From the tool's own definition: "Tool name 'execute_cli_script' directly indicates execution of CLI scripts. The sibling tools (add_custom_command_to_template, add_policies_to_block, add_ips_rule, etc.) all involve network security policy modifications through FortiManager, confirming this…"

## Use case

AI agents invoke execute_cli_script to trigger actions in Fortimanager. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Fortimanager:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_cli_script": {
      "limits": [
        {
          "counter": "execute_cli_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Fortimanager (583)

- `bulk_delete_security_profile_entries` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/bulk-delete-security-profile-entries.md
- `clear_database_cache` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/clear-database-cache.md
- `delete_adom_revision` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-adom-revision.md
- `delete_central_dnat_policy` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-central-dnat-policy.md
- `delete_central_snat_policy` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-central-snat-policy.md
- `delete_certificate_template` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-certificate-template.md
- `delete_cli_script` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-cli-script.md
- `delete_cli_template` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-cli-template.md
- `delete_cli_template_group` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-cli-template-group.md
- `delete_custom_application` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-custom-application.md
- `delete_device_blueprint` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-device-blueprint.md
- `delete_device_group` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-device-group.md
- `delete_dns_filter_domain` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-dns-filter-domain.md
- `delete_dynamic_interface` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-dynamic-interface.md
- `delete_external_threat_feed` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-external-threat-feed.md
- `delete_firewall_address` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-firewall-address.md
- `delete_firewall_policy` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-firewall-policy.md
- `delete_firewall_zone` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-firewall-zone.md
- `delete_fortiap_profile` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-fortiap-profile.md
- `delete_fortiextender` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-fortiextender.md
- `delete_internet_service_fqdn` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-internet-service-fqdn.md
- `delete_internet_service_group` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-internet-service-group.md
- `delete_ip_pool` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-ip-pool.md
- `delete_ips_sensor` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-ips-sensor.md
- `delete_ipsec_phase1_interface` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-ipsec-phase1-interface.md
- `delete_ipsec_phase2_interface` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-ipsec-phase2-interface.md
- `delete_ipsec_template` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-ipsec-template.md
- `delete_meta_field` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-meta-field.md
- `delete_object_metadata` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-object-metadata.md
- `delete_policy_block` — Destructive — https://policylayer.com/tools/jmpijll-fortimanager-mcp/delete-policy-block.md
- …and 553 more: https://policylayer.com/tools/jmpijll-fortimanager-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=jmpijll-fortimanager-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/jmpijll-fortimanager-mcp