Skip to main content
Glama
powerdrillai

Powerdrill MCP Server

Official
by powerdrillai

mcp_powerdrill_create_job

Analyze Powerdrill datasets by creating AI-powered analysis jobs to answer natural language questions about your data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesThe natural language question or prompt to analyze the data
dataset_idYesThe ID of the dataset to analyze
datasource_idsNoOptional array of specific data source IDs within the dataset to analyze
session_idYesSession ID to group related jobs
streamNoWhether to stream the results (default: false)
output_languageNoThe language for the output (default: AUTO)AUTO
job_modeNoThe job mode (default: AUTO)AUTO

Implementation Reference

  • MCP handler function that parses arguments, calls PowerdrillClient.createJob, processes the response blocks (simplifying TABLE/IMAGE), formats as MCP content, handles errors
    async (args, extra) => {
      try {
        // Initialize Powerdrill client
        const client = new (await import('./utils/powerdrillClient.js')).PowerdrillClient();
    
        // Create job parameters
        const jobParams = {
          question: args.question,
          dataset_id: args.dataset_id,
          datasource_ids: args.datasource_ids,
          session_id: args.session_id,
          stream: args.stream,
          output_language: args.output_language,
          job_mode: args.job_mode
        };
    
        // Create job
        const response = await client.createJob(jobParams);
    
        // Check if response is valid
        if (response.code !== 0 || !response.data) {
          throw new Error(`Invalid API response: ${JSON.stringify(response)}`);
        }
    
        // Process blocks for a cleaner response
        const processedBlocks = response.data.blocks.map((block: any) => {
          // For TABLE and IMAGE types, just include the URL and name
          if (block.type === 'TABLE' || block.type === 'IMAGE') {
            return {
              type: block.type,
              url: block.content.url,
              name: block.content.name,
              expires_at: block.content.expires_at
            };
          }
    
          // For other types, keep the original content
          return {
            type: block.type,
            content: block.content,
            stage: block.stage
          };
        });
    
        // Format the response as MCP content
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify({
                job_id: response.data.job_id,
                blocks: processedBlocks
              }, null, 2)
            }
          ]
        };
      } catch (error: any) {
        console.error(`Error creating job: ${error.message}`);
    
        // Return error response
        return {
          content: [
            {
              type: "text",
              text: `Error creating job: ${error.message}`
            }
          ],
          isError: true
        };
      }
    }
  • Zod input schema defining parameters for the mcp_powerdrill_create_job tool
    {
      question: z.string().describe('The natural language question or prompt to analyze the data'),
      dataset_id: z.string().describe('The ID of the dataset to analyze'),
      datasource_ids: z.array(z.string()).optional().describe('Optional array of specific data source IDs within the dataset to analyze'),
      session_id: z.string().describe('Session ID to group related jobs'),
      stream: z.boolean().optional().default(false).describe('Whether to stream the results (default: false)'),
      output_language: z.string().optional().default('AUTO').describe('The language for the output (default: AUTO)'),
      job_mode: z.string().optional().default('AUTO').describe('The job mode (default: AUTO)')
    },
  • src/index.ts:187-269 (registration)
    Registration of the mcp_powerdrill_create_job tool on the MCP server using server.tool
    server.tool(
      'mcp_powerdrill_create_job',
      {
        question: z.string().describe('The natural language question or prompt to analyze the data'),
        dataset_id: z.string().describe('The ID of the dataset to analyze'),
        datasource_ids: z.array(z.string()).optional().describe('Optional array of specific data source IDs within the dataset to analyze'),
        session_id: z.string().describe('Session ID to group related jobs'),
        stream: z.boolean().optional().default(false).describe('Whether to stream the results (default: false)'),
        output_language: z.string().optional().default('AUTO').describe('The language for the output (default: AUTO)'),
        job_mode: z.string().optional().default('AUTO').describe('The job mode (default: AUTO)')
      },
      async (args, extra) => {
        try {
          // Initialize Powerdrill client
          const client = new (await import('./utils/powerdrillClient.js')).PowerdrillClient();
    
          // Create job parameters
          const jobParams = {
            question: args.question,
            dataset_id: args.dataset_id,
            datasource_ids: args.datasource_ids,
            session_id: args.session_id,
            stream: args.stream,
            output_language: args.output_language,
            job_mode: args.job_mode
          };
    
          // Create job
          const response = await client.createJob(jobParams);
    
          // Check if response is valid
          if (response.code !== 0 || !response.data) {
            throw new Error(`Invalid API response: ${JSON.stringify(response)}`);
          }
    
          // Process blocks for a cleaner response
          const processedBlocks = response.data.blocks.map((block: any) => {
            // For TABLE and IMAGE types, just include the URL and name
            if (block.type === 'TABLE' || block.type === 'IMAGE') {
              return {
                type: block.type,
                url: block.content.url,
                name: block.content.name,
                expires_at: block.content.expires_at
              };
            }
    
            // For other types, keep the original content
            return {
              type: block.type,
              content: block.content,
              stage: block.stage
            };
          });
    
          // Format the response as MCP content
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify({
                  job_id: response.data.job_id,
                  blocks: processedBlocks
                }, null, 2)
              }
            ]
          };
        } catch (error: any) {
          console.error(`Error creating job: ${error.message}`);
    
          // Return error response
          return {
            content: [
              {
                type: "text",
                text: `Error creating job: ${error.message}`
              }
            ],
            isError: true
          };
        }
      }
    );
  • PowerdrillClient.createJob helper method that performs the actual API POST request to /jobs endpoint
    /**
     * Create a job to analyze data with natural language questions
     * @param params Parameters for creating a job
     * @returns Promise with the job result
     */
    async createJob(params: CreateJobParams) {
      try {
        // Include user_id in the request body
        const requestBody = {
          ...params,
          user_id: this.config.userId
        };
    
        const response = await this.client.post('/jobs', requestBody);
        return response.data;
      } catch (error: any) {
        console.error('Error creating job:', error.message);
        throw error;
      }
    }
  • TypeScript interface defining parameters for createJob in PowerdrillClient
    export interface CreateJobParams {
      session_id: string;
      question: string;
      dataset_id: string;
      datasource_ids?: string[];
      stream?: boolean;
      output_language?: string;
      job_mode?: string;
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/powerdrillai/powerdrill-mcp'

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