AI agents call juno_version to retrieve information from Junobuild without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays version metadata from the Juno CLI and emulator. It has no side effects, does not modify data, does not execute arbitrary code, and does not affect system state. It is purely informational, making it a Read-category tool with low severity.
From the tool's definition Tool description states 'Show the current versions' — a query operation that retrieves version information without modifying or executing anything. The --version flag pattern is a standard informational read-only operation.
Attacks that exploit this kind of access
Show the current versions of the Juno CLI and emulator (if running). Use --version flag. It is categorised as a Read tool in the Junobuild MCP Server, which means it retrieves data without modifying state.
Register the Junobuild MCP server in PolicyLayer and add a rule for juno_version: 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_version 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 juno_version 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_version. 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_version 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 →