返回单篇证据被引用的原文部分（高亮内容）
AI agents call evidence_highlight 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 retrieves and highlights excerpts from medical evidence documents for presentation purposes. It is a read-only operation that queries and displays data without creating, modifying, deleting, or executing external operations. The function is informational retrieval within a medical evidence analysis system.
From the tool's definition Tool name 'evidence_highlight' and description '返回单篇证据被引用的原文部分（高亮内容）' [returns highlighted portions of original text cited in a single piece of evidence] indicate retrieval and display of existing content with no modifications, deletions, or side effects.
Attacks that exploit this kind of access
返回单篇证据被引用的原文部分（高亮内容）. 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_highlight: 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_highlight 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_highlight 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_highlight. 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_highlight 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 →