AI agents use websocket_osc_control to create or update resources in MCP2OSC — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP2OSC environment.
An AI agent can call websocket_osc_control faster than any human can review — one bad instruction and it creates or modifies resources in MCP2OSC by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Real-time OSC parameter control via WebSocket. Enables live parameter streaming and real-time control. It is categorised as a Write tool in the MCP2OSC MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP2OSC MCP server in PolicyLayer and add a rule for websocket_osc_control: 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 MCP2OSC. Nothing to install.
websocket_osc_control is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the websocket_osc_control 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 websocket_osc_control. 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.
websocket_osc_control is provided by the MCP2OSC MCP server (yyf/mcp2osc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.