scope_capabilities
AI agents call scope_capabilities to retrieve information from LeCroy Oscilloscope MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'scope_capabilities' strongly implies a read/query operation that retrieves what the oscilloscope can do (supported features, models, modes). No description is provided, which lowers confidence. Based on naming conventions and context of sibling tools (connect, status, channel_info), this appears to be a read-only informational query with minimal blast radius.
From the tool's definition Tool name 'scope_capabilities' and empty description; name suggests querying device capabilities
Attacks that exploit this kind of access
scope_capabilities. It is categorised as a Read tool in the LeCroy Oscilloscope MCP MCP Server, which means it retrieves data without modifying state.
Register the LeCroy Oscilloscope MCP server in PolicyLayer and add a rule for scope_capabilities: 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 LeCroy Oscilloscope MCP. Nothing to install.
scope_capabilities 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 scope_capabilities 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 scope_capabilities. 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.
scope_capabilities is provided by the LeCroy Oscilloscope MCP server (lucasgerads/lecroy-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 →