Set a config option in a Jujutsu (jj) repository. Updates either user or repo config file. Parameters: name (Name of config option to set), value (Value to set), user (Optional flag to set user-level config), repo (Optional flag to set repo-level config), repoPath (Optional path to repo root or w...
AI agents use config-set 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.
The tool modifies configuration files in a Jujutsu repository or user-level config, which qualifies as a Write operation (creates or modifies data reversibly). However, severity is high rather than medium because config changes can have broad impacts on repository behavior, CI/CD pipelines, or user workflows depending on what options are set.
From the tool's definition Tool description explicitly states it "Updates either user or repo config file" with parameters to set config options at user or repository level. This is a reversible modification operation.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Set a config option in a Jujutsu (jj) repository. Updates either user or repo config file. Parameters: name (Name of config option to set), value (Value to set), user (Optional flag to set user-level config), repo (Optional flag to set repo-level config), repoPath (Optional path to repo root or working directory), cwd (Optional working directory to run the command in). 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 config-set: 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.
config-set 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 config-set 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 config-set. 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.
config-set 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 →