audit_runtime_readiness
Audit the installed machine instead of trusting the static capability matrix: required binaries, Chrome, Apple Vision, local voice, configured generation providers, and irreducible external boundaries.
This record as markdown: /tools/cutpilot/audit-runtime-readiness.md
What audit_runtime_readiness does on Cutpilot
AI agents call audit_runtime_readiness to retrieve information from Cutpilot without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why audit_runtime_readiness is rated Low
This tool inspects and reads the local machine's configuration, installed software, and capability state. It performs discovery/querying of the environment without modifying anything. 'Audit' in this context means checking/verifying what is present, not making changes. Severity is low as it only reads system state, though it could expose sensitive environment configuration details.
From the tool's definition Audit the installed machine... required binaries, Chrome, Apple Vision, local voice, configured generation providers
Attacks that exploit this kind of access
The rule that runs audit_runtime_readiness safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cutpilot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For audit_runtime_readiness, this is the rule to start with:
audit_runtime_readiness is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cutpilot, apply this rule, and every audit_runtime_readiness call is checked against it from then on.
Questions about audit_runtime_readiness
Audit the installed machine instead of trusting the static capability matrix: required binaries, Chrome, Apple Vision, local voice, configured generation providers, and irreducible external boundaries. It is categorised as a Read tool in the Cutpilot MCP Server, which means it retrieves data without modifying state.
Register the Cutpilot MCP server in PolicyLayer and add a rule for audit_runtime_readiness: 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 Cutpilot. Nothing to install.
audit_runtime_readiness 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 audit_runtime_readiness 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 audit_runtime_readiness. 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.
audit_runtime_readiness is provided by the Cutpilot MCP server (Hellotravisss/cutpilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cutpilot, and thousands of servers like it.
This server
Across the catalogue