AI agents call get_latest_orchestration to retrieve information from Yunxiao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
appName | string | Yes | Application name. Use list_applications to discover valid app names. |
envName | string | Yes | Environment name. Use list_environments to discover valid environment names. |
organizationId | string | — | Yunxiao organization ID. When omitted, the server uses the user's default organization. |
Parameters from the server's own tool schema.
This tool retrieves deployment orchestration metadata for an application environment. The verb 'Get' and context of fetching configuration data with no side effects place this firmly in the Read category. The blast radius is minimal—an agent can only view orchestration details, not alter infrastructure or deployments.
From the tool's definition Tool name and description both indicate retrieval: 'Get the latest available AppStack orchestration' with no modification, deletion, or execution capability. It queries deployment configuration and resource layout information.
Attacks that exploit this kind of access
Get the latest available AppStack orchestration for an application environment. Orchestrations define the deployment configuration and resource layout. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
get_latest_orchestration accepts 3 parameters: appName, envName, organizationId. Required: appName, envName. The full parameter table on this page comes from the server's own tool schema.
Register the Yunxiao MCP server in PolicyLayer and add a rule for get_latest_orchestration: 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 Yunxiao. Nothing to install.
get_latest_orchestration 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 get_latest_orchestration 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 get_latest_orchestration. 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.
get_latest_orchestration is provided by the Yunxiao MCP server (@futuretea/yunxiao-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 →