AI agents call get_track_status 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 is a straightforward read operation that queries the current processing status of documents. It has no side effects, does not modify data, and does not execute code or delete anything. The blast radius of misuse is minimal—an attacker could at worst learn status information about existing documents.
From the tool's definition Tool name 'get_track_status' and description 'Get the processing status of documents by tracking ID' indicate a query operation that retrieves status information without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Get the processing status of documents by tracking ID. 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_track_status: 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_track_status 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_track_status 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_track_status. 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_track_status 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 →