Read the current system clipboard text content (SDK mode).
AI agents call sdk_clipboard_read to retrieve information from UI Bridge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves clipboard data without side effects or modifications. While clipboard may contain sensitive information (passwords, tokens, PII), the tool itself performs only passive observation. Severity is low because clipboard reading alone does not enable damage; risk depends entirely on what data happens to be in the clipboard at that moment, which is outside the tool's control.
From the tool's definition Tool name 'sdk_clipboard_read' and description 'Read the current system clipboard text content' explicitly indicate read-only clipboard access with no modification capability.
Attacks that exploit this kind of access
Read the current system clipboard text content (SDK mode). It is categorised as a Read tool in the UI Bridge MCP MCP Server, which means it retrieves data without modifying state.
Register the UI Bridge MCP server in PolicyLayer and add a rule for sdk_clipboard_read: 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 UI Bridge MCP. Nothing to install.
sdk_clipboard_read 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 sdk_clipboard_read 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 sdk_clipboard_read. 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.
sdk_clipboard_read is provided by the UI Bridge MCP server (qontinui/ui-bridge-mcp). 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 →