analyze_command
Analyze a shell command for safety risks without executing it. Returns risk level (SAFE/WARNING/DANGEROUS/BLOCKED), reasons, and recommendations.
This record as markdown: /tools/7majesty-m-terminal-guardian-mcp/analyze-command.md
What analyze_command does on Terminal Guardian
AI agents call analyze_command to retrieve information from Terminal Guardian without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why analyze_command is rated Low
This is a read operation that queries command safety without modifying state or executing external actions. While it exists in a context of other tools that can execute commands, analyze_command itself only performs analysis and returns information. The tool is a safeguard mechanism designed to prevent misuse of other tools, making it fundamentally informational rather than actionable.
From the tool's definition analyze_command performs static analysis and returns risk assessments without executing anything. The description explicitly states it analyzes 'without executing it' and returns risk levels and recommendations.
Attacks that exploit this kind of access
The rule that runs analyze_command safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Terminal Guardian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For analyze_command, this is the rule to start with:
analyze_command is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Terminal Guardian, apply this rule, and every analyze_command call is checked against it from then on.
Questions about analyze_command
Analyze a shell command for safety risks without executing it. Returns risk level (SAFE/WARNING/DANGEROUS/BLOCKED), reasons, and recommendations. It is categorised as a Read tool in the Terminal Guardian MCP Server, which means it retrieves data without modifying state.
Register the Terminal Guardian MCP server in PolicyLayer and add a rule for analyze_command: 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 Terminal Guardian. Nothing to install.
analyze_command 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 analyze_command 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 analyze_command. 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.
analyze_command is provided by the Terminal Guardian MCP server (7majesty-m/terminal-guardian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Terminal Guardian, and thousands of servers like it.
This server
Across the catalogue