High-level guided MCP flow for buying and onboarding a Yaver managed cloud machine. Always returns status and post-purchase repo/credential sync steps. Only creates a checkout URL when confirm_checkout=true AND accept_cost=true, after explicit user approval.
AI agents call yaver_managed_cloud_onboarding to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
region | string | — | eu default |
repo_query | string | — | Optional app/repo name to deploy after the cloud machine is ready |
accept_cost | boolean | — | Must be true with confirm_checkout after explicit user approval of billable managed cloud |
git_provider | string | — | |
machine_type | string | — | cpu default; gpu for heavier/model workloads |
start_git_oauth | boolean | — | Optionally start GitHub/GitLab Device Flow while preparing cloud onboarding |
confirm_checkout | boolean | — | Set true only after the user asks to buy/start checkout |
Parameters from the server's own tool schema.
Even though yaver_managed_cloud_onboarding only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
High-level guided MCP flow for buying and onboarding a Yaver managed cloud machine. Always returns status and post-purchase repo/credential sync steps. Only creates a checkout URL when confirm_checkout=true AND accept_cost=true, after explicit user approval. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
yaver_managed_cloud_onboarding accepts 7 parameters: region, repo_query, accept_cost, git_provider, machine_type, start_git_oauth, confirm_checkout. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for yaver_managed_cloud_onboarding: 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 Yaver. Nothing to install.
yaver_managed_cloud_onboarding 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 yaver_managed_cloud_onboarding 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 yaver_managed_cloud_onboarding. 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.
yaver_managed_cloud_onboarding is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.