Return shard information for one or all indices.
AI agents call get_shards to retrieve information from Odigo Elastic S2l without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic/operational information about Elasticsearch shard allocation and status. It does not modify data, execute queries against indexed data, trigger external operations, delete data, or move money. The information returned is informational metadata about cluster topology, which is typically accessible to users with read permissions.
From the tool's definition Tool name 'get_shards' and description 'Return shard information for one or all indices' indicate a read-only query operation that retrieves cluster metadata about shard distribution and status.
Attacks that exploit this kind of access
Return shard information for one or all indices. It is categorised as a Read tool in the Odigo Elastic S2l MCP Server, which means it retrieves data without modifying state.
Register the Odigo Elastic S2l MCP server in PolicyLayer and add a rule for get_shards: 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 Odigo Elastic S2l. Nothing to install.
get_shards 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 get_shards 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 get_shards. 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.
get_shards is provided by the Odigo Elastic S2l MCP server (rbeg1/odigo-elastic-s2l-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 →