AI agents call parse_evtx to retrieve information from SIFTGuard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and parses existing Windows Event Log files to extract and filter log entries. It performs read-only forensic analysis with no side effects—no data is created, modified, or deleted. Severity is medium because it accesses potentially sensitive security logs containing user activity, logon events, process creation, and privilege changes, which could expose sensitive information if misused.
From the tool's definition Parse Windows Event Log (.evtx) file and filter by Event IDs
Attacks that exploit this kind of access
Parse Windows Event Log (.evtx) file and filter by Event IDs. Key IDs: 4624=logon, 4688=process, 4720=new_user, 4698=scheduled_task, 7045=service. It is categorised as a Read tool in the SIFTGuard MCP Server, which means it retrieves data without modifying state.
Register the SIFTGuard MCP server in PolicyLayer and add a rule for parse_evtx: 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 SIFTGuard. Nothing to install.
parse_evtx 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 parse_evtx 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 parse_evtx. 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.
parse_evtx is provided by the SIFTGuard MCP server (sodiq-code/siftguard). 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 →