AI agents call query_knowledge_graph to retrieve information from RAG-Anything MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context establish this as a querying/retrieval function with no inherent capability to modify or delete data. Query operations are fundamentally Read category—they retrieve information without side effects.
From the tool's definition Tool name 'query_knowledge_graph' indicates a read operation on a knowledge graph. Server description lists 'query modes (naive, local, global, hybrid)' as core RAG functionality, positioning this as a retrieval operation.
Documented attack patterns abuse exactly the kind of access query_knowledge_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAG-Anything MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_knowledge_graph:
{
"version": "1",
"default": "deny",
"tools": {
"query_knowledge_graph": {}
}
}query_knowledge_graph 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.
query_knowledge_graph. It is categorised as a Read tool in the RAG-Anything MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RAG-Anything MCP Server MCP server in PolicyLayer and add a rule for query_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 RAG-Anything MCP Server. Nothing to install.
query_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 query_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 query_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.
query_knowledge_graph is provided by the RAG-Anything MCP Server MCP server (serkanyasr/rag-anythink-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAG-Anything MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 RAG-Anything MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.