AI agents use file-chmod to create or update resources in Jj — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jj environment.
This tool modifies file permissions (the executable bit) within a version control repository. While it alters file metadata, this is a reversible write operation—permissions can be changed back. It does not delete data (Destructive), execute arbitrary code (Execute), or trigger financial operations (Financial).
From the tool's definition Tool description states it "Sets or removes the executable bit for files in a Jujutsu (jj) repository". The verb "sets" indicates modification of file metadata (permissions), which is a reversible change operation.
Attacks that exploit this kind of access
Sets or removes the executable bit for files in a Jujutsu (jj) repository. Unlike POSIX chmod, this works on Windows and on arbitrary revisions. Parameters: mode (Mode to set,. It is categorised as a Write tool in the Jj MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jj MCP server in PolicyLayer and add a rule for file-chmod: 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 Jj. Nothing to install.
file-chmod 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 file-chmod 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 file-chmod. 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.
file-chmod is provided by the Jj MCP server (jj-mcp-server). 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 →