Write input to a terminal session. Commands add a newline by default, but you can disable that for raw control sequences.
AI agents invoke write_terminal to trigger actions in Persistent Terminal MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Writing to a terminal session is functionally equivalent to executing arbitrary shell commands. The blast radius is critical because an AI agent could send any command (file deletion, network calls, privilege escalation, etc.) to a persistent terminal session that survives disconnection.
From the tool's definition 'Write input to a terminal session. Commands add a newline by default' — writing input to a terminal session causes arbitrary command execution in a persistent shell environment.
Attacks that exploit this kind of access
Write input to a terminal session. Commands add a newline by default, but you can disable that for raw control sequences. It is categorised as a Execute tool in the Persistent Terminal MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Persistent Terminal MCP Server MCP server in PolicyLayer and add a rule for write_terminal: 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 Persistent Terminal MCP Server. Nothing to install.
write_terminal is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the write_terminal 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 write_terminal. 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.
write_terminal is provided by the Persistent Terminal MCP Server MCP server (masx200/persistent-terminal-mcp). 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 →