AI agents use make_dir_func to create or update resources in Fs Git — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fs Git environment.
Creating a directory is a reversible write operation—directories can be deleted and changes can be undone via git history or reverting commits. This is less severe than destructive operations (which cannot be undone) but more impactful than read-only operations.
From the tool's definition Tool name 'make_dir_func' and description 'Create directory' indicate creation of a filesystem object. The server description states it 'enforc[es] commits on writes', confirming this is a write operation that triggers git commits.
Attacks that exploit this kind of access
Create directory. It is categorised as a Write tool in the Fs Git MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fs Git MCP server in PolicyLayer and add a rule for make_dir_func: 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 Fs Git. Nothing to install.
make_dir_func 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 make_dir_func 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 make_dir_func. 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.
make_dir_func is provided by the Fs Git MCP server (wojons/fs-git-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 →