consult_knowledge_graph
AI agents call consult_knowledge_graph to retrieve information from Asset Aware without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only consultation of a knowledge graph resource. Knowledge graph queries typically retrieve structured information without side effects. No evidence of data modification, deletion, execution, or financial operations. Severity is low because retrieving research data from a knowledge graph poses minimal risk of harm when misused by an AI agent.
From the tool's definition Tool name 'consult_knowledge_graph' indicates a query/retrieval operation against a knowledge graph. The server description emphasizes 'retrieve and analyze' capabilities with 'knowledge graph integration' for research purposes.
Attacks that exploit this kind of access
consult_knowledge_graph. It is categorised as a Read tool in the Asset Aware MCP Server, which means it retrieves data without modifying state.
Register the Asset Aware MCP server in PolicyLayer and add a rule for consult_knowledge_graph: 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 Asset Aware. Nothing to install.
consult_knowledge_graph 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 consult_knowledge_graph 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 consult_knowledge_graph. 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.
consult_knowledge_graph is provided by the Asset Aware MCP server (u9401066/asset-aware-mcp). 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 →