Set the current working directory for a connection
AI agents use ssh_set_working_directory to create or update resources in SSH MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SSH MCP Server environment.
This tool modifies session state reversibly (the working directory can be changed back). It does not execute arbitrary code, delete data, or transfer funds. However, it is not purely a Read operation since it changes state.
From the tool's definition Tool description: 'Set the current working directory for a connection' — this modifies the state of an SSH session by changing the working directory, which affects subsequent operations on that connection.
Attacks that exploit this kind of access
Set the current working directory for a connection. It is categorised as a Write tool in the SSH MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SSH MCP Server MCP server in PolicyLayer and add a rule for ssh_set_working_directory: 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 SSH MCP Server. Nothing to install.
ssh_set_working_directory 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 ssh_set_working_directory 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 ssh_set_working_directory. 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.
ssh_set_working_directory is provided by the SSH MCP Server MCP server (widjis/mcp-ssh). 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 →