windows_ntfs_mft
AI agents call windows_ntfs_mft to retrieve information from Velociraptor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The NTFS MFT is a system metadata structure that records file information on Windows systems. Reading it is a forensic read operation with no side effects or data modification. However, assigned medium severity due to the forensic context and potential exposure of sensitive system metadata that could inform further malicious actions if misused by an agent, though the tool itself only reads existing data.
From the tool's definition Tool name 'windows_ntfs_mft' indicates retrieval of NTFS Master File Table (MFT) metadata. No destructive language ('delete','drop','purge') present.
Attacks that exploit this kind of access
windows_ntfs_mft. It is categorised as a Read tool in the Velociraptor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Velociraptor MCP Server MCP server in PolicyLayer and add a rule for windows_ntfs_mft: 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 Velociraptor MCP Server. Nothing to install.
windows_ntfs_mft 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 windows_ntfs_mft 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 windows_ntfs_mft. 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.
windows_ntfs_mft is provided by the Velociraptor MCP Server MCP server (snoe-findley/mcp-velociraptor). 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 →