返回当前 MCP 工具分类目录（与 tool_metadata 及 category_registry 一致）。
AI agents call tools_catalog to retrieve information from TdxQuant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists information about tools and their categorization—a read-only operation with no side effects. It provides data about the system's tool catalog without modifying, executing, or deleting anything. The blast radius if misused is minimal, as it only exposes tool metadata that the system should already acknowledge exists.
From the tool's definition Tool name 'tools_catalog' and description '返回当前 MCP 工具分类目录' (returns the current MCP tool classification directory) indicate a retrieval operation that queries and returns metadata about available tools.
Documented attack patterns abuse exactly the kind of access tools_catalog gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TdxQuant MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for tools_catalog:
{
"version": "1",
"default": "deny",
"tools": {
"tools_catalog": {}
}
}tools_catalog is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
返回当前 MCP 工具分类目录（与 tool_metadata 及 category_registry 一致）。. It is categorised as a Read tool in the TdxQuant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TdxQuant MCP Server MCP server in PolicyLayer and add a rule for tools_catalog: 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 TdxQuant MCP Server. Nothing to install.
tools_catalog 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 tools_catalog 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 tools_catalog. 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.
tools_catalog is provided by the TdxQuant MCP Server MCP server (lingfan/tdxquant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TdxQuant MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
39 TdxQuant MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.