Query Lucene index with optional metadata filter and top_k.
AI agents call lucene_query to retrieve information from Mcp Lucene without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a Lucene search index. The description explicitly indicates it queries an index and filters results, which are read-only operations with no side effects. The presence of sibling tools like 'lucene_delete' and 'lucene_upsert' confirms this tool is distinct and read-only in nature.
From the tool's definition Tool name is 'lucene_query' and description states 'Query Lucene index with optional metadata filter and top_k' - describes a search/query operation with no mention of modification or deletion.
Attacks that exploit this kind of access
Query Lucene index with optional metadata filter and top_k. It is categorised as a Read tool in the Mcp Lucene MCP Server, which means it retrieves data without modifying state.
Register the Mcp Lucene MCP server in PolicyLayer and add a rule for lucene_query: 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 Mcp Lucene. Nothing to install.
lucene_query 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 lucene_query 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 lucene_query. 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.
lucene_query is provided by the Mcp Lucene MCP server (vivekkumarneu/mcp-lucene-server). 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 →