AI agents invoke juno_functions_upgrade to trigger actions in Junobuild. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Upgrading a satellite involves deploying new code or configuration to a live system, which is an external operation with significant impact. It goes beyond a simple write (it replaces running software), but may not be strictly irreversible if rollback is possible. The blast radius is high since a botched upgrade could break a production satellite.
From the tool's definition 'Upgrade your satellite' — triggers an upgrade operation on a deployed satellite
Attacks that exploit this kind of access
Upgrade your satellite. It is categorised as a Execute tool in the Junobuild MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Junobuild MCP server in PolicyLayer and add a rule for juno_functions_upgrade: 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_functions_upgrade is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the juno_functions_upgrade 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_functions_upgrade. 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_functions_upgrade 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 →