Search for database objects (tables, views, stored procedures, functions, triggers) by name pattern. Supports SQL LIKE wildcards (% for any characters, _ for single character).
AI agents call search_objects to retrieve information from Sql Database without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
server | string | Yes | Server hostname (e.g. server1.database.windows.net) |
database | string | Yes | Database name |
search_pattern | string | Yes | Name pattern to search for. Use % as wildcard (e.g. %invoice%, Customer%, %_audit) |
Parameters from the server's own tool schema.
This tool retrieves metadata about database objects without executing queries, modifying data, or triggering side effects. It is purely informational—similar to the sibling tools like list_tables and get_table_schema. The blast radius of misuse is minimal; an attacker could enumerate object names but cannot read data, execute code, or modify the database.
From the tool's definition Tool description states it 'Search[es] for database objects' by name pattern, which is a query/discovery operation with no modification capability. The wildcard support (LIKE pattern matching) is consistent with read-only schema inspection.
Attacks that exploit this kind of access
Search for database objects (tables, views, stored procedures, functions, triggers) by name pattern. Supports SQL LIKE wildcards (% for any characters, _ for single character). It is categorised as a Read tool in the Sql Database MCP Server, which means it retrieves data without modifying state.
search_objects accepts 3 parameters: server, database, search_pattern. Required: server, database, search_pattern. The full parameter table on this page comes from the server's own tool schema.
Register the Sql Database MCP server in PolicyLayer and add a rule for search_objects: 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 Sql Database. Nothing to install.
search_objects 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 search_objects 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 search_objects. 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.
search_objects is provided by the Sql Database MCP server (sql-database-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 →