Get detailed (not filtered) information for a specific database. Returns comprehensive database details including configuration, status, cluster information, and associated resources. When to Use: - Get detailed information about a single, specific database - Access database-specific properties n...
AI agents call get_database to retrieve information from NDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries existing database information without creating, modifying, deleting, or executing any operations. It is a pure read operation that has no side effects on the Nutanix Database Service environment. The blast radius of misuse is minimal as the worst outcome would be unauthorized data disclosure of database configuration details.
From the tool's definition Tool name is 'get_database' and description states it 'Get detailed information for a specific database' and 'Returns comprehensive database details including configuration, status, cluster information, and associated resources.' The guidance explicitly…
Attacks that exploit this kind of access
Get detailed (not filtered) information for a specific database. Returns comprehensive database details including configuration, status, cluster information, and associated resources. When to Use: - Get detailed information about a single, specific database - Access database-specific properties not available in list_databases - Retrieve complete infrastructure and configuration details - DO NOT use for multiple databases - use list_databases with filters instead Unique Information Available (not in list_databases): - Complete database configuration and engine-specific properties - Detailed infrastructure information in databaseNodes array - Associated dbservers collection with full details - Linked databases information with creation details - Complete time machine details (when detailed=true) - Resource utilization and extended metadata Database Properties (engine-specific): - Oracle: PDB/CDB configuration, tablespace details, archive settings - PostgreSQL: extensions, shared_preload_libraries, custom parameters - SQL Server: availability groups, backup compression, collation settings - All engines: version specifics, port configurations, data paths Infrastructure Details: - databaseNodes array: complete VM and cluster information - linkedDatabases array: shows user vs system-created databases (info.created_by) - dbservers collection: hosting infrastructure details Search Options with Examples: - By ID (most precise): databaseId=. It is categorised as a Read tool in the NDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NDB MCP Server MCP server in PolicyLayer and add a rule for get_database: 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 NDB MCP Server. Nothing to install.
get_database 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_database 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_database. 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_database is provided by the NDB MCP Server MCP server (rouxton/ndb-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 →