AI agents call fs_pwd to retrieve information from Emcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query the current working directory and return it to the caller. This is a read operation with no capability to modify, delete, or execute. Even in a context with other destructive filesystem tools on the server, this specific tool only retrieves information.
From the tool's definition Tool name 'fs_pwd' indicates print working directory operation. No description provided, but 'pwd' is a standard Unix command that retrieves the current directory path without side effects.
Attacks that exploit this kind of access
fs_pwd. It is categorised as a Read tool in the Emcp MCP Server, which means it retrieves data without modifying state.
Register the E MCP server in PolicyLayer and add a rule for fs_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 Emcp. Nothing to install.
fs_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 fs_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 fs_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.
fs_pwd is provided by the E MCP server (slezica/emcp). 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 →