Gets information about shards in OpenSearch.
AI agents call GetShardsTool to retrieve information from Opensearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries shard information, which is a retrieval operation with no destructive, modifying, or execution capability. It aligns with the Read category (retrieves or queries data; no side effects). The severity is low because reading shard metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description states 'Gets information about shards in OpenSearch' — a read-only operation that retrieves shard metadata without modifying or executing operations. No side effects are indicated.
Attacks that exploit this kind of access
Gets information about shards in OpenSearch. It is categorised as a Read tool in the Opensearch MCP Server, which means it retrieves data without modifying state.
Register the Opensearch MCP server in PolicyLayer and add a rule for GetShardsTool: 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. Nothing to install.
GetShardsTool 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 GetShardsTool 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 GetShardsTool. 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.
GetShardsTool is provided by the Opensearch MCP server (rithinpullela/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 →