Search documents in an index with a custom query
AI agents call search_documents to retrieve information from mcp-OpenSearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from OpenSearch indices without modifying, deleting, or executing arbitrary operations. While it accepts a 'custom query', the scope is limited to search operations, which are read-only by nature. The broader server context shows this is part of document retrieval tooling alongside other read-only cluster and index inspection tools.
From the tool's definition Tool name 'search_documents' and description 'Search documents in an index with a custom query' indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Search documents in an index with a custom query. It is categorised as a Read tool in the mcp-OpenSearch MCP Server, which means it retrieves data without modifying state.
Register the mcp-OpenSearch MCP server in PolicyLayer and add a rule for search_documents: 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-OpenSearch. Nothing to install.
search_documents 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_documents 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_documents. 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_documents is provided by the mcp-OpenSearch MCP server (showjason/opensearch-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 →