Press a key on the keyboard.
AI agents use playcaller_key_press to create or update resources in Playcaller — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Playcaller environment.
An AI agent can call playcaller_key_press faster than any human can review — one bad instruction and it creates or modifies resources in Playcaller by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Press a key on the keyboard. It is categorised as a Write tool in the Playcaller MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Playcaller MCP server in PolicyLayer and add a rule for playcaller_key_press: 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 Playcaller. Nothing to install.
playcaller_key_press 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 playcaller_key_press 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 playcaller_key_press. 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.
playcaller_key_press is provided by the Playcaller MCP server (takashicompany/playcaller). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.