AI agents call os_nvda_status to retrieve information from OScribe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves the current status of the NVDA screen reader without modifying any system state, executing arbitrary code, or triggering side effects. It is a pure read operation that queries the state of an accessibility tool. The low severity reflects minimal blast radius—an AI agent misusing this would only retrieve status information without causing harm.
From the tool's definition Tool performs a status check on NVDA screen reader ("Check NVDA screen reader status") with no indication of modification, deletion, or execution of commands.
Attacks that exploit this kind of access
Check NVDA screen reader status (Windows only). NVDA is needed for Electron app accessibility. It is categorised as a Read tool in the OScribe MCP Server, which means it retrieves data without modifying state.
Register the OScribe MCP server in PolicyLayer and add a rule for os_nvda_status: 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 OScribe. Nothing to install.
os_nvda_status 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 os_nvda_status 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 os_nvda_status. 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.
os_nvda_status is provided by the OScribe MCP server (mikealkeal/oscribe). 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 →