AI agents call config-get to retrieve information from Jj without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration values from a Jujutsu repository without creating, modifying, or deleting data. It is a read-only query operation with no side effects or potential for misuse to cause damage.
From the tool's definition Tool name 'config-get' and description 'Get the value of a config option' indicate retrieval of configuration data without modification.
Attacks that exploit this kind of access
Get the value of a config option in a Jujutsu (jj) repository. Unlike. It is categorised as a Read tool in the Jj MCP Server, which means it retrieves data without modifying state.
Register the Jj MCP server in PolicyLayer and add a rule for config-get: 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-get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the config-get 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-get. 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-get 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 →