sdk_network_requests_in_flight
AI agents call sdk_network_requests_in_flight 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.
The tool appears to monitor or query active network requests, which is a read-only inspection operation with no side effects. The empty description lowers confidence, but the name strongly suggests passive observation rather than modification or execution of commands. No risk of data loss, code execution, or financial harm.
From the tool's definition Tool name 'sdk_network_requests_in_flight' suggests it retrieves or inspects the status of network requests in flight; no destructive action indicated by the name.
Attacks that exploit this kind of access
sdk_network_requests_in_flight. 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_network_requests_in_flight: 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_network_requests_in_flight 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_network_requests_in_flight 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_network_requests_in_flight. 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_network_requests_in_flight 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 →