View text files or directory listings. Binary files are detected and rejected with instructions to read SKILL documentation. If you've lost track of your environment (chat_id, file URLs, available skills), re-read /home/assistant/README.md. Supported path types: - Directories: Lists files and dir...
AI agents call view to retrieve information from Open Computer Use without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves and displays file contents or directory information. No data is created, modified, deleted, or executed. The tool's purpose is inspection/querying only. Severity is low because viewing files in a controlled Docker workspace poses minimal risk—the workspace is already isolated, and read access alone cannot cause harm.
From the tool's definition Tool displays text files or directory listings. Explicitly rejects binary files. Returns data without modification or side effects.
Documented attack patterns abuse exactly the kind of access view gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Open Computer Use, and nothing reaches the server without passing your rules. This is the rule we recommend for view:
{
"version": "1",
"default": "deny",
"tools": {
"view": {}
}
}view is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
View text files or directory listings. Binary files are detected and rejected with instructions to read SKILL documentation. If you've lost track of your environment (chat_id, file URLs, available skills), re-read /home/assistant/README.md. Supported path types: - Directories: Lists files and directories with details - Text files: Displays numbered lines. You can optionally specify a view_range. - Binary files (.xlsx, .docx, .pptx, .pdf, etc.): Returns error with SKILL.md instructions Args: description: Why I need to view this path: Absolute path to file or directory, e.g. /repo/file.py or /repo view_range: Optional line range [start_line, end_line]. Use [start, -1] to view from start to end. Returns: File contents, directory listing, or error message. It is categorised as a Read tool in the Open Computer Use MCP Server, which means it retrieves data without modifying state.
Register the Open Computer Use MCP server in PolicyLayer and add a rule for view: 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 Open Computer Use. Nothing to install.
view 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 view 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 view. 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.
view is provided by the Open Computer Use MCP server (wide-moat/open-computer-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Open Computer Use tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Open Computer Use tools catalogued and risk-classified — across an index of 42,500+ MCP servers.