This record as markdown: /tools/cowork-bench/canvas-list-notifications.md
What canvas_list_notifications does on Cowork Bench
AI agents call canvas_list_notifications to retrieve information from Cowork Bench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why canvas_list_notifications is rated Low
This tool retrieves or queries notification data for a user with no apparent side effects, modifications, or destructive capabilities. It fits the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch)'. The description is somewhat sparse, which slightly reduces confidence, but the naming pattern and 'list' operation clearly indicate a read-only query function.
From the tool's definition Tool name 'canvas_list_notifications' and description 'List user' indicate retrieval of notification data without modification. The verb 'list' and action of retrieving user notifications are characteristic of Read operations.
Attacks that exploit this kind of access
The rule that runs canvas_list_notifications safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For canvas_list_notifications, this is the rule to start with:
canvas_list_notifications 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 Cowork Bench, apply this rule, and every canvas_list_notifications call is checked against it from then on.
Questions about canvas_list_notifications
List user. It is categorised as a Read tool in the Cowork Bench MCP Server, which means it retrieves data without modifying state.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for canvas_list_notifications: 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 Bench. Nothing to install.
canvas_list_notifications 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 canvas_list_notifications 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_list_notifications. 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_list_notifications is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue