Search documents in an opensearch index with a custom query
AI agents invoke search_documents to trigger actions in OpenSearch MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While searching is primarily a read operation, 'custom query' implies the tool executes arbitrary query DSL against OpenSearch. OpenSearch queries can include scripted fields, update_by_query-style operations, or expensive aggregations that could impact cluster performance. The execution of arbitrary queries elevates this above a simple Read, though it lacks explicit write/destructive capabilities described.
From the tool's definition Search documents in an opensearch index with a custom query
Documented attack patterns abuse exactly the kind of access search_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenSearch MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_documents:
{
"version": "1",
"default": "deny",
"tools": {
"search_documents": {
"limits": [
{
"counter": "search_documents_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}search_documents stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search documents in an opensearch index with a custom query. It is categorised as a Execute tool in the OpenSearch MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenSearch MCP Server 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 OpenSearch MCP Server. Nothing to install.
search_documents is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 OpenSearch MCP Server MCP server (seohyunjun/opensearch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenSearch MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 OpenSearch MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.