AI agents call kb_semantic_search 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 tool queries a knowledge base using semantic similarity without side effects. It retrieves information but does not create, modify, delete, or execute operations. The sibling tools like 'kb_read_section' and 'kb_keyword_search' further confirm this is part of a read-only knowledge base access layer. Severity is low as misuse would only expose already-stored information.
From the tool's definition Tool name and description indicate 'kb_semantic_search' performs vector-based semantic retrieval using natural language or synonym concepts.
Attacks that exploit this kind of access
向量语义检索（自然语言/近义概念）。. 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_semantic_search: 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_semantic_search 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_semantic_search 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_semantic_search. 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_semantic_search 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_semantic_search 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 →