Get all registered and provisioned database instances with comprehensive filtering options. Returns a list of database objects with summarized information including status, type, ownership, etc. The detailed information about each database instance (properties) is not included by default to optim...
AI agents call list_databases 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 performs a read-only query operation to retrieve and list database instances. It has no side effects, cannot modify or delete data, and does not execute external commands. The optional 'detailed' parameter merely controls the verbosity of the returned information. This is a straightforward inventory/discovery operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states it "Get all registered and provisioned database instances" and "Returns a list of database objects with summarized information." The operation is purely informational retrieval with optional detailed parameter; no data modification,…
Attacks that exploit this kind of access
Get all registered and provisioned database instances with comprehensive filtering options. Returns a list of database objects with summarized information including status, type, ownership, etc. The detailed information about each database instance (properties) is not included by default to optimize performance, but can be included by setting the detailed parameter to true. The detailed information can be useful in some cases, for instance if you want to get the database version, the VM ip address, listener port, etc. If not available with the detailed option, use get_database tool to get detailed information about a specific database instance. Best Practices: - Always use specific filters to get exactly what you need rather than broad queries - Use properties filters (requires detailed=true) for version-specific searches - Combine multiple filters to narrow results efficiently Available Filters (valueType/value pairs): - name: Database instance name in NDB (supports partial matching with *pattern*) - description: Database instance description text - ownerId: User ID who owns the database instance (use list_users to resolve usernames) - dateCreated/dateModified: Date filters (use >YYYY-MM-DD, <YYYY-MM-DD for comparisons) - clustered: true/false - whether database instance is clustered - eraCreated: true/false - NDB-provisioned (greenfield) vs registered (brownfield) - databaseName: Database instance name on the VM (may differ from instance name) - type: Database engine type (postgres_database, oracle_database, sqlserver_database, mariadb_database, mysql_database, saphana_database, mongodb_database) - status: Operational status (READY=operational, ERA_DAEMON_UNREACHABLE=agent issues, PROVISIONING=in progress, FAILED=error state) - dbserverLogicalClusterId: Logical cluster hosting the database - timeMachineId: Associated time machine for backups - properties.version: Database engine version. Examples: - PostgreSQL: 11, 12, 13, 14, 15, 16 (use >=15.5, >14, etc.) - Oracle: 12c, 19c, 21c (use >12c, <19c, etc.) - SQL Server: 2016, 2017, 2019, 2022 (use >=2019, etc.) Properties are available only if detailed=true. Advanced Filtering: - Operators: !value (not), >value/<value (comparison), *value* (contains) - Multiple filters: combine with comma-separated valueType/value pairs - Example: Find PostgreSQL production databases: valueType=. 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 list_databases: 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.
list_databases 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 list_databases 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 list_databases. 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.
list_databases 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 →