Generate a juno.config file (TypeScript, JavaScript, or JSON). By default returns config content for preview. Set writeFile to true to write the file directly to disk. Then run juno_config_apply to push the config to your satellite.
AI agents use juno_config_init 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 creates a configuration file on disk. When writeFile is true, it writes to the filesystem, which is a reversible Write action (the file can be overwritten or deleted). It doesn't execute commands, delete data irreversibly, or move money. The blast radius is medium since a misconfigured juno.config could affect satellite behavior when subsequently applied.
From the tool's definition Generate a juno.config file... Set writeFile to true to write the file directly to disk.
Attacks that exploit this kind of access
Generate a juno.config file (TypeScript, JavaScript, or JSON). By default returns config content for preview. Set writeFile to true to write the file directly to disk. Then run juno_config_apply to push the config to your satellite. 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_init: 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_init 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_init 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_init. 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_init 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 →