results_files
AI agents call results_files to retrieve information from CyPerf MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates file retrieval rather than modification, deletion, or execution. Accessing test result files is a non-destructive read operation. Despite the empty description, the naming convention and context of a testing/analysis platform suggest this retrieves pre-computed results rather than triggering new operations or modifying data.
From the tool's definition Tool name 'results_files' suggests retrieval of result files from completed tests. The name pattern matches other Read operations like 'agents_get' and 'agents_list' in the sibling tools. The empty description reduces confidence slightly.
Attacks that exploit this kind of access
results_files. It is categorised as a Read tool in the CyPerf MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CyPerf MCP Server MCP server in PolicyLayer and add a rule for results_files: 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 CyPerf MCP Server. Nothing to install.
results_files 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 results_files 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 results_files. 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.
results_files is provided by the CyPerf MCP Server MCP server (keysight/cyperf-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 →