get_table_indexes
AI agents call get_table_indexes to retrieve information from Oracle MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns index metadata for a table—a non-destructive read operation with no side effects. Even if misused by an agent, it only retrieves information about database structure. Severity is low because reading schema metadata poses minimal risk compared to data modification or deletion.
From the tool's definition Tool name 'get_table_indexes' follows read-only pattern (get_*) for retrieving schema metadata. No description provided, but context from sibling tools shows this server exposes both read operations (get_*) and write/execute operations (exec_*).
Attacks that exploit this kind of access
get_table_indexes. It is categorised as a Read tool in the Oracle MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Oracle MCP Server MCP server in PolicyLayer and add a rule for get_table_indexes: 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 Oracle MCP Server. Nothing to install.
get_table_indexes 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_table_indexes 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_table_indexes. 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_table_indexes is provided by the Oracle MCP Server MCP server (zhengwanbo/oracle-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 →