AI agents call get_documents_paginated to retrieve information from Lightrag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries documents using pagination, which is a standard read operation. It has no side effects—it does not create, modify, delete, or execute anything. The pagination parameter allows controlled retrieval of data without altering system state. This is categorized as Read with low severity, as unauthorized or excessive reads may have limited blast radius in typical scenarios.
From the tool's definition Tool name 'get_documents_paginated' and description 'Retrieve documents with pagination support' indicate a retrieval operation with no data modification.
Attacks that exploit this kind of access
Retrieve documents with pagination support. It is categorised as a Read tool in the Lightrag MCP Server, which means it retrieves data without modifying state.
Register the Lightrag MCP server in PolicyLayer and add a rule for get_documents_paginated: 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. Nothing to install.
get_documents_paginated 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 get_documents_paginated 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 get_documents_paginated. 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.
get_documents_paginated is provided by the Lightrag MCP server (lightrag-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 →