llm_status
Check whether the LLM backend is available and report its configuration.
This record as markdown: /tools/nyxstrike/llm-status.md
What llm_status does on Nyxstrike
AI agents call llm_status to retrieve information from Nyxstrike without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why llm_status is rated Low
This tool only queries and reports the status and configuration of an LLM backend. It retrieves information without creating, modifying, executing, or deleting anything. Despite operating on a penetration testing platform, the specific function is purely informational—checking availability and reading configuration state.
From the tool's definition Tool name 'llm_status' and description 'Check whether the LLM backend is available and report its configuration' indicate this performs a status check and retrieval of configuration information with no side effects.
Attacks that exploit this kind of access
The rule that runs llm_status safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nyxstrike, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For llm_status, this is the rule to start with:
llm_status 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 Nyxstrike, apply this rule, and every llm_status call is checked against it from then on.
Questions about llm_status
Check whether the LLM backend is available and report its configuration. It is categorised as a Read tool in the Nyxstrike MCP Server, which means it retrieves data without modifying state.
Register the Nyxstrike MCP server in PolicyLayer and add a rule for llm_status: 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 Nyxstrike. Nothing to install.
llm_status 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 llm_status 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 llm_status. 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.
llm_status is provided by the Nyxstrike MCP server (CommonHuman-Lab/nyxstrike). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nyxstrike, and thousands of servers like it.
This server
Across the catalogue