search_index
AI agents call search_index to retrieve information from NRTSearch MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_index retrieves data from indexes without modifying or deleting anything. It performs a search query operation, which is inherently a Read category action. No side effects, reversible operations, code execution, data destruction, or financial impact. The tool's context among other informational read tools (get_*) confirms this classification.
From the tool's definition Tool is part of NRTSearch server which 'search[es] and query[ies] Lucene/NRTSearch indexes using natural language' and 'supporting full Lucene query syntax'.
Attacks that exploit this kind of access
search_index. It is categorised as a Read tool in the NRTSearch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NRTSearch MCP Server MCP server in PolicyLayer and add a rule for search_index: 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 NRTSearch MCP Server. Nothing to install.
search_index 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_index 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_index. 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_index is provided by the NRTSearch MCP Server MCP server (tvergilio/nrtsearch-mcp-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 →