基于问题和检索出来的证据，生成场景总结（收集完整的流式响应后返回）
AI agents call answer_stream 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 medical evidence data and produces summaries or answers—a retrieval and analysis operation with no side effects on the underlying data. It does not create persistent records, execute code/commands, delete data, or move money. The streaming aspect is a delivery mechanism, not an action category change. This is a Read operation in the medical evidence retrieval context.
From the tool's definition Tool description states it 'generates scenario summaries based on questions and retrieved evidence' with 'streaming response'. The verb 'generates' here means synthesizing/summarizing existing data rather than modifying or deleting it.
Attacks that exploit this kind of access
基于问题和检索出来的证据，生成场景总结（收集完整的流式响应后返回）. 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 answer_stream: 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.
answer_stream 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 answer_stream 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 answer_stream. 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.
answer_stream 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 →