AI agents call get_developer_usage 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 |
|---|---|---|---|
page | number | — | Page number for pagination. Starts at 1. |
userId | string | — | User ID to query usage for a specific developer. Use list_organization_members to discover valid user IDs. Either userId or departmentId must be provided. |
endTime | string | Yes | End time for the usage query range (inclusive). Format: yyyy-MM-ddTHH:mm:ss+08:00. |
perPage | number | — | Page size for pagination. Supports 1-100. Defaults to 100 when omitted. |
startTime | string | Yes | Start time for the usage query range (inclusive). Format: yyyy-MM-ddTHH:mm:ss+08:00 (e.g. 2024-01-01T00:00:00+08:00). |
departmentId | string | — | Department ID to query usage for all developers in a department. Use list_organization_departments to discover valid department IDs. Either userId or department |
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 queries and retrieves usage metrics for analysis purposes. It performs a read-only operation on historical usage data with no capability to modify, delete, or execute external operations. The blast radius is minimal as misuse would only expose usage visibility across developers/departments.
From the tool's definition Tool description states 'Get Tongyi Lingma usage metrics' and 'analyze individual or team AI coding assistant usage' — retrieves metrics/usage data with no modification or side effects.
Attacks that exploit this kind of access
Get Tongyi Lingma usage metrics for a specific developer or department over a time range. Use this to analyze individual or team AI coding assistant usage. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
get_developer_usage accepts 7 parameters: page, userId, endTime, perPage, startTime, departmentId, organizationId. Required: endTime, startTime. 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_developer_usage: 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_developer_usage 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_developer_usage 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_developer_usage. 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_developer_usage 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 →