Simplified global mode query - Best for relationship discovery. Focuses on understanding relationships and connections between different aspects of your domains.
AI agents call query_global to retrieve information from Knowledge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information from a knowledge base without modifying, deleting, or executing external operations. It returns relationship data for discovery purposes, which is characteristic of a Read operation. The low severity reflects that querying a knowledge base has minimal blast radius—it cannot alter data, trigger external systems, or cause financial impact.
From the tool's definition Tool description explicitly states it is a 'query' operation that 'Focuses on understanding relationships and connections' and retrieves information from knowledge bases.
Documented attack patterns abuse exactly the kind of access query_global gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Knowledge, and nothing reaches the server without passing your rules. This is the rule we recommend for query_global:
{
"version": "1",
"default": "deny",
"tools": {
"query_global": {}
}
}query_global is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Simplified global mode query - Best for relationship discovery. Focuses on understanding relationships and connections between different aspects of your domains. It is categorised as a Read tool in the Knowledge MCP Server, which means it retrieves data without modifying state.
Register the Knowledge MCP server in PolicyLayer and add a rule for query_global: 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 Knowledge. Nothing to install.
query_global 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_global 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_global. 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_global is provided by the Knowledge MCP server (olafgeibig/knowledge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Knowledge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Knowledge tools catalogued and risk-classified — across an index of 42,500+ MCP servers.