preview_install
AI agents invoke preview_install to trigger actions in FortiManager MCP Server. 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.
In FortiManager context, 'install' operations push configurations to live firewall devices, which is an Execute-level action with high blast radius. 'Preview' may indicate a dry-run (Read), but without a description we cannot confirm this is truly non-side-effecting. Given the ambiguity, Execute is the most appropriate category, with reduced confidence due to the empty description.
From the tool's definition Tool name 'preview_install' on a FortiManager server that manages firewall policy and device provisioning; description is empty.
Attacks that exploit this kind of access
preview_install. It is categorised as a Execute tool in the FortiManager MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FortiManager MCP Server MCP server in PolicyLayer and add a rule for preview_install: 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 FortiManager MCP Server. Nothing to install.
preview_install is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the preview_install 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.
Set action: deny in the PolicyLayer policy for preview_install. 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.
preview_install is provided by the FortiManager MCP Server MCP server (rstierli/fortimanager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →