terminal_write_file
AI agents use terminal_write_file to create or update resources in Global MCP Manager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Global MCP Manager environment.
This tool creates or modifies files, which is a reversible Write operation. However, severity is elevated to 'high' rather than 'medium' because it operates across multiple privileged contexts (local system, remote SSH servers, GitHub) where file writes could have significant downstream effects on system configuration, code repositories, or infrastructure.
From the tool's definition Tool name 'terminal_write_file' and server description stating 'file operations' and 'managing files across different contexts: local system, remote SSH servers, and GitHub repositories' indicate file modification capability.
Attacks that exploit this kind of access
terminal_write_file. It is categorised as a Write tool in the Global MCP Manager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Global MCP Manager MCP server in PolicyLayer and add a rule for terminal_write_file: 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 Global MCP Manager. Nothing to install.
terminal_write_file 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 terminal_write_file 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 terminal_write_file. 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.
terminal_write_file is provided by the Global MCP Manager MCP server (mamprimauto/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 →