AI agents call search_labels 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 performs a search operation with fuzzy matching on labels, which is a read-only retrieval operation. It does not create, modify, delete, execute external operations, or involve financial transactions. The fuzzy matching is a search algorithm, not code execution. The blast radius of misuse is minimal—an agent could only retrieve labels it already has access to, with no side effects.
From the tool's definition Tool name 'search_labels' and description 'Search labels with fuzzy matching' indicate a query/search operation that retrieves data without modifying state.
Attacks that exploit this kind of access
Search labels with fuzzy matching. 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 search_labels: 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.
search_labels 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 search_labels 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 search_labels. 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.
search_labels 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 →