AI agents use juno_functions_publish 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.
Publishing a new version of serverless functions deploys code to a live satellite environment. This is a Write/Deploy action that modifies the running state of the satellite by replacing or updating the deployed WASM module. While it could be considered Execute due to deploying executable code, the primary action is publishing/uploading a new version (a write operation).
From the tool's definition Publish a new version of your serverless functions to the satellite
Attacks that exploit this kind of access
Publish a new version of your serverless functions to the satellite. Optionally submit as a pending change without applying, or provide a custom WASM file path. 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_functions_publish: 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_publish 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_functions_publish 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_publish. 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_publish 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 →