AI agents invoke functions_rebuild to trigger actions in Run402. 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.
Rebuilding/refreshing functions onto a platform constitutes executing an external operation (redeployment), which can affect running services. It is not purely a write (data modification) nor destructive (not deleting), but it does trigger an active platform-side process whose effects depend on the current function definitions.
From the tool's definition 'Refresh function(s) onto the platform' — triggers a rebuild/redeployment operation of functions on the infrastructure platform
Attacks that exploit this kind of access
Refresh function(s) onto the platform. It is categorised as a Execute tool in the Run402 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Run402 MCP server in PolicyLayer and add a rule for functions_rebuild: 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 Run402. Nothing to install.
functions_rebuild 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 functions_rebuild 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 functions_rebuild. 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.
functions_rebuild is provided by the Run402 MCP server (kychee-com/run402). 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 →