根据用户问题搜索相关的数据库表结构，返回表名、字段名、字段类型和注释。
AI agents call schema_search to retrieve information from Utility MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and retrieves schema metadata (table and field information) based on a user question. This is a read-only operation that retrieves data without side effects. Although it provides database schema information, this is non-sensitive structural metadata commonly available to authorized users. No data modification, deletion, or code execution occurs.
From the tool's definition Tool description states 'search' for 'database table structure' and 'returns table names, field names, field types and comments' — purely informational retrieval with no modification, deletion, or execution.
Attacks that exploit this kind of access
根据用户问题搜索相关的数据库表结构，返回表名、字段名、字段类型和注释。. It is categorised as a Read tool in the Utility MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Utility MCP Server MCP server in PolicyLayer and add a rule for schema_search: 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 Utility MCP Server. Nothing to install.
schema_search 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 schema_search 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 schema_search. 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.
schema_search is provided by the Utility MCP Server MCP server (love-gwen2025/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 →