AI agents call kb_outline to retrieve information from Workhour without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only tool that retrieves organizational metadata from a knowledge base. It queries structure and returns information for viewing purposes—classic Read category behavior. Low severity due to no side effects; knowledge base outline structure is typically non-sensitive operational metadata.
From the tool's definition Tool name 'kb_outline' and description indicate it retrieves and displays knowledge base structure (directory outline, titles, h2 headers, metadata). The verb 'see' (看全貌 = 'see the full picture') indicates querying/viewing without modification.
Attacks that exploit this kind of access
知识库目录大纲（标题+h2+metadata），问题模糊时先看全貌。. It is categorised as a Read tool in the Workhour MCP Server, which means it retrieves data without modifying state.
Register the Workhour MCP server in PolicyLayer and add a rule for kb_outline: 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 Workhour. Nothing to install.
kb_outline 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 kb_outline 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 kb_outline. 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.
kb_outline is provided by the Workhour MCP server (Calvin-Ca/workhour-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
kb_outline is one line of Workhour's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →