List active device-board stream connections.
AI agents call pushtodisplay_list_devices to retrieve information from Pushtodisplay without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about active device connections. It is purely observational with no side effects, modifications, or external operations triggered. The 'list' action is a classic Read operation. Severity is low because disclosure of connection metadata poses minimal risk compared to tools that can send updates, delete boards, or execute code.
From the tool's definition Tool name contains 'list' and description states 'List active device-board stream connections' — a query operation that retrieves connection status without modifying or executing anything.
Attacks that exploit this kind of access
List active device-board stream connections. It is categorised as a Read tool in the Pushtodisplay MCP Server, which means it retrieves data without modifying state.
Register the Pushtodisplay MCP server in PolicyLayer and add a rule for pushtodisplay_list_devices: 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 Pushtodisplay. Nothing to install.
pushtodisplay_list_devices 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 pushtodisplay_list_devices 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 pushtodisplay_list_devices. 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.
pushtodisplay_list_devices is provided by the Pushtodisplay MCP server (pushtodisplay/cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →