tmux_find_text
AI agents call tmux_find_text to retrieve information from TmuxControlLib MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries text data from tmux panes or session history with no side effects. Severity is medium rather than low because text extracted from terminal sessions could contain sensitive information (credentials, API keys, private data), and an agent misusing this could exfiltrate such data, though the tool itself performs no destructive or system-altering actions.
From the tool's definition Tool name 'find_text' combined with sibling tools 'capture_history', 'capture_pane', and 'extract_table' indicates this searches or extracts text from terminal output without modification.
Attacks that exploit this kind of access
tmux_find_text. It is categorised as a Read tool in the TmuxControlLib MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TmuxControlLib MCP Server MCP server in PolicyLayer and add a rule for tmux_find_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 TmuxControlLib MCP Server. Nothing to install.
tmux_find_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 tmux_find_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 tmux_find_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.
tmux_find_text is provided by the TmuxControlLib MCP Server MCP server (jbwinters/tmuxcontrollib). 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 →