AI agents call help to retrieve information from Niscope without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a documentation/information retrieval tool that displays usage guidance. It performs no configuration changes, data acquisition, or control operations on the oscilloscope. It has no capability to modify state and presents negligible risk even if invoked by an agent.
From the tool's definition The tool name is 'help' and description states it 'Show[s] usage guide, parameter reference, and typical workflow examples' — purely informational retrieval with no side effects on device state or data.
Attacks that exploit this kind of access
Show usage guide, parameter reference, and typical workflow examples. It is categorised as a Read tool in the Niscope MCP Server, which means it retrieves data without modifying state.
Register the Niscope MCP server in PolicyLayer and add a rule for 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 Niscope. Nothing to install.
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 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 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.
help is provided by the Niscope MCP server (ymzds/niscope-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
help is one line of Niscope's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →