AI agents call get_clean_text to retrieve information from Repl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_clean_text only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Get clean terminal text without ANSI escape codes. Returns either the current line (where cursor is) or full terminal content depending on the fullText parameter. It is categorised as a Read tool in the Repl MCP Server, which means it retrieves data without modifying state.
Register the Repl MCP server in PolicyLayer and add a rule for get_clean_text: 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 Repl. Nothing to install.
get_clean_text 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_clean_text 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_clean_text. 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_clean_text is provided by the Repl MCP server (takafu/repl-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.