AI agents call kb_keyword_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 performs a search operation (keyword/term/number lookup) against a knowledge base using BM25 ranking. It retrieves information without creating, modifying, deleting, or executing code. No side effects or data mutations occur. This is a classic Read operation—it queries and returns search results only.
From the tool's definition Tool name 'kb_keyword_search' and description 'BM25 关键词检索（精确术语/编号/数字）' indicates keyword-based search functionality. BM25 is a retrieval algorithm used for information retrieval without modification of underlying data.
Attacks that exploit this kind of access
BM25 关键词检索（精确术语/编号/数字）。. 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_keyword_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_keyword_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_keyword_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_keyword_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_keyword_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_keyword_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 →