記錄知識使用反饋,用於持續優化知識品質
AI agents use record_knowledge_feedback to create or update resources in EKMS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your EKMS MCP Server environment.
This tool records user feedback on knowledge items, which is a write operation (creating new feedback records). It does not delete data, execute code, or involve financial transactions. Misuse would have minimal blast radius as it only affects feedback/quality metadata in the knowledge system.
From the tool's definition 記錄知識使用反饋 (Record knowledge usage feedback) — creates/writes feedback data; 持續優化知識品質 (continuously optimize knowledge quality) indicates a write operation to store feedback
Attacks that exploit this kind of access
記錄知識使用反饋,用於持續優化知識品質. It is categorised as a Write tool in the EKMS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the EKMS MCP Server MCP server in PolicyLayer and add a rule for record_knowledge_feedback: 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 EKMS MCP Server. Nothing to install.
record_knowledge_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_knowledge_feedback 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 record_knowledge_feedback. 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.
record_knowledge_feedback is provided by the EKMS MCP Server MCP server (jihsin/ekms-mcp-server). 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 →