AI agents call tecton_cli_help to retrieve information from Tecton without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Help/documentation retrieval is a read-only operation with no side effects. It queries information about available commands without modifying, executing, or deleting anything. The lack of a description lowers confidence slightly, but the tool name and sibling context make Read the clear category. Severity is low as misuse would only retrieve documentation.
From the tool's definition Tool name 'tecton_cli_help' strongly indicates it retrieves help/documentation for Tecton CLI commands. No description provided, but the naming convention and context among sibling tools (which are predominantly Read operations like list_* and get_*) supports…
Attacks that exploit this kind of access
tecton_cli_help. It is categorised as a Read tool in the Tecton MCP Server, which means it retrieves data without modifying state.
Register the Tecton MCP server in PolicyLayer and add a rule for tecton_cli_help: 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 Tecton. Nothing to install.
tecton_cli_help 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 tecton_cli_help 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 tecton_cli_help. 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.
tecton_cli_help is provided by the Tecton MCP server (slavovthinks/tecton-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 →