AI agents invoke edit to trigger actions in Jj. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool changes the working-copy state by switching to a different revision, which is an active operation affecting the working directory. It triggers external VCS operations and modifies repository state, but is generally reversible. It fits Execute better than Write since it triggers a VCS operation rather than creating/modifying data content directly.
From the tool's definition Sets the specified revision as the working-copy revision in a Jujutsu (jj) repository
Attacks that exploit this kind of access
Sets the specified revision as the working-copy revision in a Jujutsu (jj) repository. Note: it is generally recommended to instead use. It is categorised as a Execute tool in the Jj MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Jj MCP server in PolicyLayer and add a rule for edit: 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.
edit is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the edit 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 edit. 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.
edit 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 →