Lists WebSocket connections or gets messages for a specific connection. Without wsid, lists all connections. With wsid, gets messages. Set analyze=true to group messages by pattern. Use groupId to filter by group. Use frameIndex to get a single message
AI agents call get_websocket_messages to retrieve information from JS Reverse MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and inspects WebSocket communication data for debugging purposes. While it can expose sensitive application state and communication patterns (warranting medium severity in a misuse context), it performs no write, destructive, execute, or financial operations. The sibling tool 'clear_site_data' is destructive; 'evaluate_script' is execute; but this tool itself only reads.
From the tool's definition Tool description states it 'Lists WebSocket connections or gets messages for a specific connection' and 'gets messages' — purely retrieval operations with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Lists WebSocket connections or gets messages for a specific connection. Without wsid, lists all connections. With wsid, gets messages. Set analyze=true to group messages by pattern. Use groupId to filter by group. Use frameIndex to get a single message. It is categorised as a Read tool in the JS Reverse MCP MCP Server, which means it retrieves data without modifying state.
Register the JS Reverse MCP server in PolicyLayer and add a rule for get_websocket_messages: 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 JS Reverse MCP. Nothing to install.
get_websocket_messages 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 get_websocket_messages 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 get_websocket_messages. 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.
get_websocket_messages is provided by the JS Reverse MCP server (zhizhuodemao/js-reverse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.