project.audit
Queue an authoritative scene audit with canonical-unit and safe-mode findings.
This record as markdown: /tools/visionmcp/project.audit.md
What project.audit does on Visionmcp
AI agents call project.audit to retrieve information from Visionmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why project.audit is rated Low
An audit is an inspection/verification activity that reads and reports on data, similar to a compliance review or log analysis. There is no indication the tool creates, modifies, executes commands, deletes data, or commits financial obligations. The queuing mechanism suggests asynchronous read operations only.
From the tool's definition 'Queue an authoritative scene audit' — the tool performs an audit operation that retrieves or queries findings; 'canonical-unit and safe-mode findings' indicates it generates reports without modifying project state or executing external operations.
Attacks that exploit this kind of access
The rule that runs project.audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For project.audit, this is the rule to start with:
project.audit 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 Visionmcp, apply this rule, and every project.audit call is checked against it from then on.
Questions about project.audit
Queue an authoritative scene audit with canonical-unit and safe-mode findings. It is categorised as a Read tool in the Visionmcp MCP Server, which means it retrieves data without modifying state.
Register the Vision MCP server in PolicyLayer and add a rule for project.audit: 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 Visionmcp. Nothing to install.
project.audit 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 project.audit 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 project.audit. 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.
project.audit is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue