AI agents call get_user_organizations 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. Defaults to 1 when omitted by Yunxiao. |
perPage | number | — | Page size from 1 to 100. Defaults to 100 when omitted by Yunxiao. |
Parameters from the server's own tool schema.
This tool retrieves metadata about organizations accessible to the authenticated user. It performs a simple lookup that does not modify, execute, delete, or move any resources. The blast radius of misuse is minimal since the returned information is organizational metadata already visible to the user. Classified as Read with low severity.
From the tool's definition Tool description states 'Get Yunxiao organizations visible to the current user' and 'discover organization IDs and names' — this is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
Get Yunxiao organizations visible to the current user. Use this to discover organization IDs and names when the default organization is not the desired one. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
get_user_organizations accepts 2 parameters: page, perPage. 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_user_organizations: 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_user_organizations 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_user_organizations 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_user_organizations. 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_user_organizations 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 →