对单篇证据进行 AI 概要总结
AI agents call evidence_summary 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 performs evidence retrieval and analysis through summarization—a core Read operation. It queries medical evidence and generates a summary, producing no side effects, data modifications, or irreversible actions. Within the medical/evidence context of the KnowS server, summarization is a non-destructive analytical operation.
From the tool's definition Tool description translates to 'AI summary/summarization of a single piece of evidence' (Chinese: 对单篇证据进行 AI 概要总结). The verb 'summarize' is a read-only operation that retrieves and processes existing evidence without modifying or deleting it.
Attacks that exploit this kind of access
对单篇证据进行 AI 概要总结. 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 evidence_summary: 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.
evidence_summary 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 evidence_summary 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 evidence_summary. 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.
evidence_summary 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 →