Get a catalog of all available Yunxiao tools organized by domain. Use this when you are unsure which tool to use or want to discover what operations are supported. The returned catalog includes each tool's name, domain, description, and read-only status.
AI agents call describe_toolset 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 |
|---|---|---|---|
domain | string | — | Optional domain filter. Valid values: platform, projex, codeup, flow, packages, appstack, lingma, api. Omit to list all domains. |
Parameters from the server's own tool schema.
This tool retrieves and queries metadata about available tools in the Yunxiao system. It performs no write operations, does not delete data, does not execute code or commands, and does not create or modify state. The read-only clarification in the description further confirms this is a safe information retrieval mechanism with no potential for causing harm through misuse.
From the tool's definition Tool description states it 'Get a catalog of all available Yunxiao tools' and explicitly notes the 'read-only status' of tools. The verb 'Get' and the passive discovery nature of the operation indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Get a catalog of all available Yunxiao tools organized by domain. Use this when you are unsure which tool to use or want to discover what operations are supported. The returned catalog includes each tool's name, domain, description, and read-only status. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
describe_toolset accepts 1 parameter: domain. 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 describe_toolset: 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.
describe_toolset 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 describe_toolset 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 describe_toolset. 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.
describe_toolset 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 →