get_script_log_output
AI agents call get_script_log_output to retrieve information from FortiManager MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves log output from previously executed scripts, which is a read operation with no side effects on system state. However, log data from scripts in a centralized firewall management system could reveal sensitive operational details, network topology, or security configurations, warranting medium severity due to potential information disclosure if logs contain sensitive data.
From the tool's definition Tool name 'get_script_log_output' indicates retrieval of log data from executed scripts in FortiManager; the 'get' prefix and 'output' suggest read-only query of results without modification.
Attacks that exploit this kind of access
get_script_log_output. It is categorised as a Read tool in the FortiManager MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FortiManager MCP Server MCP server in PolicyLayer and add a rule for get_script_log_output: 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.
get_script_log_output is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_script_log_output 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 get_script_log_output. 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.
get_script_log_output 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 →