Skip to main content
Glama
LiusCraft

Superset MCP Server

by LiusCraft

list-fields

Retrieve the field list of a specified table in a database by providing the database ID, schema name, and table name, enabling structured data access for analysis.

Instructions

获取指定表的字段列表

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
databaseIdYes数据库ID
schemaYesSchema名称
tableNameYes表名

Implementation Reference

  • The main handler function for the 'list-fields' MCP tool. It fetches fields using getTableFields helper, formats them into a text list, and returns as MCP content.
    async ({ databaseId, schema, tableName }) => {
      try {
        const fields = await getTableFields(databaseId, schema, tableName);
    
        if (fields.length === 0) {
          return {
            content: [
              {
                type: "text",
                text: `表 ${schema}.${tableName} 中没有找到字段`,
              },
            ],
          };
        }
        
        const fieldsList = fields.map(field => `名称: ${field.name}, 类型: ${field.type}`).join("\n");
        
        return {
          content: [
            {
              type: "text",
              text: `表 ${schema}.${tableName} 的字段列表:\n\n${fieldsList}`,
            },
          ],
        };
      } catch (error) {
        console.error("获取字段列表失败:", error);
        return {
          content: [
            {
              type: "text",
              text: `获取字段列表失败: ${(error as Error).message}`,
            },
          ],
        };
      }
    }
  • Zod schema defining the input parameters for the list-fields tool: databaseId (number), schema (string), tableName (string).
    {
      databaseId: z.number().describe("数据库ID"),
      schema: z.string().describe("Schema名称"),
      tableName: z.string().describe("表名"),
    },
  • src/index.ts:420-465 (registration)
    Registers the 'list-fields' tool on the MCP server with name, description, input schema, and handler function.
    server.tool(
      "list-fields",
      "获取指定表的字段列表",
      {
        databaseId: z.number().describe("数据库ID"),
        schema: z.string().describe("Schema名称"),
        tableName: z.string().describe("表名"),
      },
      async ({ databaseId, schema, tableName }) => {
        try {
          const fields = await getTableFields(databaseId, schema, tableName);
    
          if (fields.length === 0) {
            return {
              content: [
                {
                  type: "text",
                  text: `表 ${schema}.${tableName} 中没有找到字段`,
                },
              ],
            };
          }
          
          const fieldsList = fields.map(field => `名称: ${field.name}, 类型: ${field.type}`).join("\n");
          
          return {
            content: [
              {
                type: "text",
                text: `表 ${schema}.${tableName} 的字段列表:\n\n${fieldsList}`,
              },
            ],
          };
        } catch (error) {
          console.error("获取字段列表失败:", error);
          return {
            content: [
              {
                type: "text",
                text: `获取字段列表失败: ${(error as Error).message}`,
              },
            ],
          };
        }
      }
    );
  • Helper function to retrieve and cache table fields using Superset API.
    async function getTableFields(databaseId: number, schema: string, tableName: string): Promise<Field[]> {
      const cacheKey = `${databaseId}:${schema}:${tableName}`;
      
      if (fieldsCache.has(cacheKey)) {
        return fieldsCache.get(cacheKey) || [];
      }
      
      try {
        const metadata = await supersetApi.getTableMetadata(databaseId, schema, tableName);
        fieldsCache.set(cacheKey, metadata.columns);
        return metadata.columns;
      } catch (error) {
        console.error(`获取表 ${schema}.${tableName} 的字段失败:`, error);
        return [];
      }
    }
  • SupersetApiService method that calls the Superset API to get table metadata (including columns/fields).
    public async getTableMetadata(databaseId: number, schemaName: string, tableName: string): Promise<TableMetadata> {
      try {
        // 使用新的 API 路径格式
        console.log(`尝试使用表元数据API: /api/v1/database/${databaseId}/table/${tableName}/${schemaName}/`);
        
        const response = await this.client.get<TableMetadata>(
          `/api/v1/database/${databaseId}/table/${tableName}/${schemaName}/`
        );
        
        if (!response.success || !response.data) {
          throw new Error(response.error?.message || `获取表 ${schemaName}.${tableName} 的元数据失败`);
        }
        
        return response.data;
      } catch (error) {
        console.error('获取表元数据失败:', error);
        throw error;
      }
    }
Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LiusCraft/superset-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server