set_working_directory
AI agents use set_working_directory to create or update resources in Codebase MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codebase MCP Server environment.
This tool changes the working directory, which is a state modification that affects subsequent operations. While reversible, it alters the execution environment and could affect which files are accessed or modified by subsequent tools. The lack of description lowers confidence slightly, but the intent is clear from the name.
From the tool's definition Tool name 'set_working_directory' indicates modification of state (working directory), which is a reversible change to the system's execution context. No description provided, limiting certainty.
Attacks that exploit this kind of access
set_working_directory. It is categorised as a Write tool in the Codebase MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codebase MCP Server MCP server in PolicyLayer and add a rule for 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 Codebase MCP Server. Nothing to install.
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 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 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.
set_working_directory is provided by the Codebase MCP Server MCP server (ravenight13/codebase-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 →