按工具名查看单个 gateway 工具的详细 schema。先用 search_gateway_tools 搜，再按需 describe。
AI agents call describe_gateway_tool to retrieve information from MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs schema introspection and retrieval—it queries metadata about other tools and returns information without modifying any state, triggering operations, or causing side effects. It is a read-only informational operation that helps users understand available tools. No data is created, modified, deleted, or any external operations are triggered.
From the tool's definition Tool description indicates it retrieves and displays detailed schema information for gateway tools using a lookup by name ('按工具名查看单个 gateway 工具的详细 schema' = 'view detailed schema of individual gateway tools by tool name').
Attacks that exploit this kind of access
按工具名查看单个 gateway 工具的详细 schema。先用 search_gateway_tools 搜，再按需 describe。. It is categorised as a Read tool in the MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the MCP Gateway MCP server in PolicyLayer and add a rule for describe_gateway_tool: 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 MCP Gateway. Nothing to install.
describe_gateway_tool 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_gateway_tool 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_gateway_tool. 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_gateway_tool is provided by the MCP Gateway MCP server (lunfengchen/gateway-mcp). 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 →