Search within indices using OpenSearch DSL (body) or query string (q).
AI agents call search_indices to retrieve information from OpenSearch MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_indices tool performs data queries and retrieval operations without modifying, deleting, or executing arbitrary code. It is a standard search function that returns results based on query parameters. While it may have access to sensitive data, the tool itself performs only read operations with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states 'Search within indices' with OpenSearch DSL or query string parameters. The name 'search_indices' and the read-only query nature confirm this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search within indices using OpenSearch DSL (body) or query string (q). It is categorised as a Read tool in the OpenSearch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenSearch MCP Server MCP server in PolicyLayer and add a rule for search_indices: 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 OpenSearch MCP Server. Nothing to install.
search_indices 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_indices 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_indices. 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_indices is provided by the OpenSearch MCP Server MCP server (suriyakumar-hait/opensearch_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 →