AI agents use juno_config_apply to create or update resources in Junobuild — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Junobuild environment.
This tool modifies configuration settings on a deployed satellite (cloud hosting platform). It updates multiple subsystems: storage headers, datastore rules, authentication config, and collection definitions. These are reversible changes (configuration can be reverted), not irreversible deletions.
From the tool's definition Apply the current juno.config file to your satellite. This is required after modifying settings like storage headers, datastore rules, authentication config, or collection definitions.
Attacks that exploit this kind of access
Apply the current juno.config file to your satellite. This is required after modifying settings like storage headers, datastore rules, authentication config, or collection definitions. It is categorised as a Write tool in the Junobuild MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Junobuild MCP server in PolicyLayer and add a rule for juno_config_apply: 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 Junobuild. Nothing to install.
juno_config_apply 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 juno_config_apply 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 juno_config_apply. 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.
juno_config_apply is provided by the Junobuild MCP server (junobuild-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 →