Get raw retrieval data (entities, relations, chunks) without LLM generation
AI agents call query_data to retrieve information from LightRAG MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval operations on knowledge graph components and document chunks. It has no capability to modify, delete, or execute operations—it only returns existing data. The 'without LLM generation' clarification confirms it is a simple data access operation rather than a generative or transformative action.
From the tool's definition Tool description explicitly states it retrieves raw data (entities, relations, chunks) 'without LLM generation'. The verb 'Get' and framing as retrieval with no side effects indicates read-only querying behavior.
Attacks that exploit this kind of access
Get raw retrieval data (entities, relations, chunks) without LLM generation. It is categorised as a Read tool in the LightRAG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LightRAG MCP Server MCP server in PolicyLayer and add a rule for query_data: 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 LightRAG MCP Server. Nothing to install.
query_data 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_data 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_data. 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_data is provided by the LightRAG MCP Server MCP server (lalitsuryan/lightragmcp). 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 →