获取Dify知识库详细信息
AI agents call dify_get_dataset_detail to retrieve information from Dify Doc 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 metadata and details about a dataset/knowledge base without modifying, executing, or deleting anything. It is a straightforward read operation with minimal risk if misused—worst case, an agent could gather information about available datasets, which is low-severity information disclosure.
From the tool's definition Tool name 'dify_get_dataset_detail' and description stating it retrieves detailed information ('获取Dify知识库详细信息' = 'Get Dify knowledge base detailed information').
Attacks that exploit this kind of access
获取Dify知识库详细信息. It is categorised as a Read tool in the Dify Doc MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dify Doc MCP Server MCP server in PolicyLayer and add a rule for dify_get_dataset_detail: 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 Dify Doc MCP Server. Nothing to install.
dify_get_dataset_detail 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 dify_get_dataset_detail 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 dify_get_dataset_detail. 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.
dify_get_dataset_detail is provided by the Dify Doc MCP Server MCP server (shellus/difydocmcpserver). 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 →