terminal_exists
AI agents call terminal_exists to retrieve information from Global MCP Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool checks whether a file or directory exists in the current context (local, SSH, or GitHub). It retrieves status information with no side effects—no data is created, modified, deleted, or executed. This is a read-only query operation. Low severity because even if misused by an agent, it merely reveals information about the file system without enabling harmful actions.
From the tool's definition Tool name 'terminal_exists' and server description indicating file operations. The 'exists' operation checks for file/directory existence without modification.
Attacks that exploit this kind of access
terminal_exists. It is categorised as a Read tool in the Global MCP Manager MCP Server, which means it retrieves data without modifying state.
Register the Global MCP Manager MCP server in PolicyLayer and add a rule for terminal_exists: 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_exists 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 terminal_exists 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_exists. 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_exists 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 →