Skip to main content
Glama
snahrup

Microsoft Fabric MCP Server

by snahrup

upload_to_datawarehouse

Upload data arrays to Microsoft Fabric Data Warehouse tables for analysis and reporting.

Instructions

Upload data to a Fabric Data Warehouse

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workspaceIdYesThe workspace ID
warehouseIdYesThe data warehouse ID
tableNameYesName of the table
dataYesArray of data rows to upload

Implementation Reference

  • The actual implementation of the tool logic that communicates with the API to upload data.
    async uploadToDataWarehouse(workspaceId: string, warehouseId: string, tableName: string, data: any[]): Promise<void> {
      try {
        // This would typically use the SQL endpoint or COPY INTO command
        const response = await this.apiClient.post(
          `/workspaces/${workspaceId}/datawarehouses/${warehouseId}/tables/${tableName}/rows`,
          { rows: data }
        );
        return response.data;
      } catch (error) {
        console.error('Error uploading to data warehouse:', error);
        throw error;
      }
    }
  • Zod schema defining the input validation for the upload_to_datawarehouse tool.
    const UploadToDataWarehouseSchema = z.object({
      workspaceId: z.string().describe('The workspace ID'),
      warehouseId: z.string().describe('The data warehouse ID'),
      tableName: z.string().describe('Name of the table'),
      data: z.array(z.any()).describe('Array of data rows to upload'),
    });
  • src/index.ts:126-150 (registration)
    MCP tool registration for upload_to_datawarehouse.
      name: 'upload_to_datawarehouse',
      description: 'Upload data to a Fabric Data Warehouse',
      inputSchema: {
        type: 'object',
        properties: {
          workspaceId: {
            type: 'string',
            description: 'The workspace ID',
          },
          warehouseId: {
            type: 'string',
            description: 'The data warehouse ID',
          },
          tableName: {
            type: 'string',
            description: 'Name of the table',
          },
          data: {
            type: 'array',
            description: 'Array of data rows to upload',
          },
        },
        required: ['workspaceId', 'warehouseId', 'tableName', 'data'],
      },
    },
  • Tool request handler in the MCP server that parses inputs and calls the fabricClient.
    case 'upload_to_datawarehouse': {
      const { workspaceId, warehouseId, tableName, data } = UploadToDataWarehouseSchema.parse(args);
      await fabricClient.uploadToDataWarehouse(workspaceId, warehouseId, tableName, data);
      return {
        content: [
          {
            type: 'text',
            text: `Data uploaded successfully to ${tableName}`,
          },
        ],
      };
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. It states the action ('Upload') which implies a write/mutation operation, but doesn't disclose critical traits like required permissions, whether data is appended/replaced, rate limits, error handling, or what happens on success/failure. This leaves significant gaps for a tool that modifies data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a tool with clear purpose and good schema documentation. Every word earns its place by conveying the essential action and target.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a data mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after upload (success confirmation, error responses), data format requirements, or system constraints. The agent lacks critical context needed to use this tool effectively in production scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are documented in the schema. The description adds no additional meaning about parameters beyond what's in the schema descriptions. It doesn't explain the relationship between workspaceId/warehouseId/tableName or provide examples of the data array format. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Upload') and target resource ('data to a Fabric Data Warehouse'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'create_notebook' or 'execute_dax_query', which are distinct operations but could be related in a data workflow context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, when-not scenarios, or how it relates to sibling tools like 'refresh_dataset' or 'execute_dax_query' in a data pipeline context. The agent must infer usage from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other 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/snahrup/microsoft-fabric-mcp'

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