os_nvda_start · OScribe MCP: Risk & Policy

WHAT IT DOES

What os_nvda_start does on OScribe

AI agents invoke os_nvda_start to trigger actions in OScribe. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why os_nvda_start needs a policy

Starting a screen reader is an Execute action rather than Read because it launches and controls an external application process, potentially affecting system behavior and accessibility settings. It's not Destructive (reversible via os_nvda_stop or restart), not Financial, and not Write (doesn't create/modify user data).

From the tool's definition Tool name 'os_nvda_start' and description 'Start NVDA screen reader in silent mode' indicates execution of an external process (NVDA screen reader application).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

os_nvda_start Rate-limited

os_nvda_start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "os_nvda_start": {
      "limits": [
        {
          "counter": "os_nvda_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches OScribe, so you can run agents against it safely.

FAQ

Questions about os_nvda_start

What does the os_nvda_start tool do? +

Start NVDA screen reader in silent mode. Required for Electron app accessibility. Windows only. It is categorised as a Execute tool in the OScribe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on os_nvda_start? +

Register the OScribe MCP server in PolicyLayer and add a rule for os_nvda_start: 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.

What risk level is os_nvda_start? +

os_nvda_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit os_nvda_start? +

Yes. Add a rate_limit block to the os_nvda_start 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.

How do I block os_nvda_start completely? +

Set action: deny in the PolicyLayer policy for os_nvda_start. 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.

What MCP server provides os_nvda_start? +

os_nvda_start 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.