获取指定表的字段列表
AI agents call list-fields to retrieve information from Superset MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about table columns/fields. It performs a read-only query against Superset to list available fields, with no ability to modify data, execute code, delete resources, or affect financial systems. The blast radius is minimal—an AI agent obtaining field metadata poses no direct security risk beyond information disclosure of schema structure.
From the tool's definition Tool name 'list-fields' and description indicate retrieval of field information from a specified table. The description translates to 'Get the field list of the specified table', which is a pure data retrieval operation with no modification or execution…
Attacks that exploit this kind of access
获取指定表的字段列表. It is categorised as a Read tool in the Superset MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Superset MCP Server MCP server in PolicyLayer and add a rule for list-fields: 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 Superset MCP Server. Nothing to install.
list-fields 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-fields 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-fields. 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-fields is provided by the Superset MCP Server MCP server (liuscraft/superset-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 →