terminal_pwd
AI agents call terminal_pwd 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.
The pwd command is a read-only operation that queries the current working directory without modifying, executing code, or performing destructive actions. Despite the server's broader capabilities for command execution and file operations, this specific tool only retrieves state information.
From the tool's definition Tool name 'terminal_pwd' is the standard Unix command to print the working directory. The server description indicates this tool operates within a multi-context environment (local, SSH, GitHub). With no side effects, this retrieves the current directory path.
Attacks that exploit this kind of access
terminal_pwd. 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_pwd: 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_pwd 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_pwd 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_pwd. 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_pwd 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 →