canvas_open_url
Open a remote web page inside the canvas window for full in-app browsing.
This record as markdown: /tools/cowork-os/canvas-open-url.md
What canvas_open_url does on CoWork OS
AI agents invoke canvas_open_url to trigger actions in CoWork OS. 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 canvas_open_url is rated High
This tool fetches and renders an arbitrary remote URL inside the application, constituting an external operation with side effects. It can trigger network requests to arbitrary destinations, potentially load malicious content, execute in-page scripts, or be used for SSRF-like attacks against internal resources. The action depends heavily on the URL argument provided, classifying it as Execute rather than a pure Read.
From the tool's definition Open a remote web page inside the canvas window for full in-app browsing
Attacks that exploit this kind of access
The rule that runs canvas_open_url safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For canvas_open_url, this is the rule to start with:
canvas_open_url 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.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every canvas_open_url call is checked against it from then on.
Questions about canvas_open_url
Open a remote web page inside the canvas window for full in-app browsing. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CoWork OS MCP server in PolicyLayer and add a rule for canvas_open_url: 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 CoWork OS. Nothing to install.
canvas_open_url is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the canvas_open_url 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 canvas_open_url. 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.
canvas_open_url is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue