Find orphaned registry entries pointing to non-existent files
AI agents call find_orphaned_entries to retrieve information from Windows Diagnostics MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs system analysis by scanning the Windows registry to identify invalid references. While it examines system state, it does not modify registry entries, delete data, execute code, or have financial impact. It is a read-only diagnostic capability that retrieves information about system inconsistencies.
From the tool's definition Tool is named 'find_orphaned_entries' and described as identifying registry entries that point to non-existent files.
Attacks that exploit this kind of access
Find orphaned registry entries pointing to non-existent files. It is categorised as a Read tool in the Windows Diagnostics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Windows Diagnostics MCP Server MCP server in PolicyLayer and add a rule for find_orphaned_entries: 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 Windows Diagnostics MCP Server. Nothing to install.
find_orphaned_entries 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 find_orphaned_entries 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 find_orphaned_entries. 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.
find_orphaned_entries is provided by the Windows Diagnostics MCP Server MCP server (jackalterman/windows-diagnostic-mcp-server). 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 →