对证据进行自动化标签提取（如研究类型、疾病领域、样本量等）
AI agents call auto_tagging to retrieve information from KnowS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes evidence content to extract categorical information, generating derived metadata tags. No data is created, modified, or deleted. The operation is non-destructive and produces only analytical output. This is a classic Read operation: querying/analyzing existing data with no side effects on the source or system state.
From the tool's definition Tool performs automatic extraction of labels/tags from evidence (research type, disease field, sample size) without modifying the underlying data. The description indicates data analysis and metadata extraction operations.
Attacks that exploit this kind of access
对证据进行自动化标签提取（如研究类型、疾病领域、样本量等）. It is categorised as a Read tool in the KnowS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KnowS MCP Server MCP server in PolicyLayer and add a rule for auto_tagging: 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 KnowS MCP Server. Nothing to install.
auto_tagging 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 auto_tagging 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 auto_tagging. 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.
auto_tagging is provided by the KnowS MCP Server MCP server (pancrepal-xiaoyibao/mcp-knows-ai). 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 →