STEP 1: Search across all knowledgelib.io knowledge units. Returns matching units ranked by relevance with metadata (confidence scores, source counts, token estimates, quality status). If no results are found, use suggest_question to request the topic.
AI agents call query_knowledge to retrieve information from Knowledgelib without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries pre-verified knowledge units without creating, modifying, deleting, or executing anything. It has no side effects beyond returning ranked search results. This is a straightforward Read operation with minimal security risk—an AI agent cannot cause harm by searching a knowledge base.
From the tool's definition Tool description explicitly states it 'Search[es] across all knowledgelib.io knowledge units' and 'Returns matching units ranked by relevance with metadata'.
Attacks that exploit this kind of access
STEP 1: Search across all knowledgelib.io knowledge units. Returns matching units ranked by relevance with metadata (confidence scores, source counts, token estimates, quality status). If no results are found, use suggest_question to request the topic. It is categorised as a Read tool in the Knowledgelib MCP Server, which means it retrieves data without modifying state.
Register the Knowledgelib MCP server in PolicyLayer and add a rule for query_knowledge: 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 Knowledgelib. Nothing to install.
query_knowledge 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 query_knowledge 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 query_knowledge. 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.
query_knowledge is provided by the Knowledgelib MCP server (peterbeck111/knowledgelib-io). 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 →