Skip to main content
Glama
powerdrillai

Powerdrill MCP Server

Official
by powerdrillai

mcp_powerdrill_create_session

Create a data analysis session to process datasets with AI-powered insights, specifying parameters like language, job mode, and context retention.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesThe session name, which can be up to 128 characters in length
output_languageNoThe language in which the output is generatedAUTO
job_modeNoJob mode for the sessionAUTO
max_contextual_job_historyNoThe maximum number of recent jobs retained as context for the next job
agent_idNoThe ID of the agentDATA_ANALYSIS_AGENT

Implementation Reference

  • src/index.ts:272-343 (registration)
    Registration of the MCP tool 'mcp_powerdrill_create_session' including input schema and handler function that delegates to PowerdrillClient.createSession
    server.tool(
      'mcp_powerdrill_create_session',
      {
        name: z.string().describe('The session name, which can be up to 128 characters in length'),
        output_language: z.enum(['AUTO', 'EN', 'ES', 'AR', 'PT', 'ID', 'JA', 'RU', 'HI', 'FR', 'DE', 'VI', 'TR', 'PL', 'IT', 'KO', 'ZH-CN', 'ZH-TW'])
          .optional()
          .default('AUTO')
          .describe('The language in which the output is generated'),
        job_mode: z.enum(['AUTO', 'DATA_ANALYTICS'])
          .optional()
          .default('AUTO')
          .describe('Job mode for the session'),
        max_contextual_job_history: z.number()
          .min(0)
          .max(10)
          .optional()
          .default(10)
          .describe('The maximum number of recent jobs retained as context for the next job'),
        agent_id: z.enum(['DATA_ANALYSIS_AGENT'])
          .optional()
          .default('DATA_ANALYSIS_AGENT')
          .describe('The ID of the agent')
      },
      async (args, extra) => {
        try {
          // Initialize Powerdrill client
          const client = new (await import('./utils/powerdrillClient.js')).PowerdrillClient();
    
          // Create session parameters
          const sessionParams = {
            name: args.name,
            output_language: args.output_language,
            job_mode: args.job_mode,
            max_contextual_job_history: args.max_contextual_job_history,
            agent_id: args.agent_id
          };
    
          // Create session
          const response = await client.createSession(sessionParams);
    
          // Check if response is valid
          if (response.code !== 0 || !response.data) {
            throw new Error(`Invalid API response: ${JSON.stringify(response)}`);
          }
    
          // Format the response as MCP content
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify({
                  session_id: response.data.id
                }, null, 2)
              }
            ]
          };
        } catch (error: any) {
          console.error(`Error creating session: ${error.message}`);
    
          // Return error response
          return {
            content: [
              {
                type: "text",
                text: `Error creating session: ${error.message}`
              }
            ],
            isError: true
          };
        }
      }
    );
  • The main handler function for the tool, which creates a PowerdrillClient instance and calls its createSession method with validated args
    async (args, extra) => {
      try {
        // Initialize Powerdrill client
        const client = new (await import('./utils/powerdrillClient.js')).PowerdrillClient();
    
        // Create session parameters
        const sessionParams = {
          name: args.name,
          output_language: args.output_language,
          job_mode: args.job_mode,
          max_contextual_job_history: args.max_contextual_job_history,
          agent_id: args.agent_id
        };
    
        // Create session
        const response = await client.createSession(sessionParams);
    
        // Check if response is valid
        if (response.code !== 0 || !response.data) {
          throw new Error(`Invalid API response: ${JSON.stringify(response)}`);
        }
    
        // Format the response as MCP content
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify({
                session_id: response.data.id
              }, null, 2)
            }
          ]
        };
      } catch (error: any) {
        console.error(`Error creating session: ${error.message}`);
    
        // Return error response
        return {
          content: [
            {
              type: "text",
              text: `Error creating session: ${error.message}`
            }
          ],
          isError: true
        };
      }
    }
  • Zod schema defining the input parameters for the mcp_powerdrill_create_session tool
    {
      name: z.string().describe('The session name, which can be up to 128 characters in length'),
      output_language: z.enum(['AUTO', 'EN', 'ES', 'AR', 'PT', 'ID', 'JA', 'RU', 'HI', 'FR', 'DE', 'VI', 'TR', 'PL', 'IT', 'KO', 'ZH-CN', 'ZH-TW'])
        .optional()
        .default('AUTO')
        .describe('The language in which the output is generated'),
      job_mode: z.enum(['AUTO', 'DATA_ANALYTICS'])
        .optional()
        .default('AUTO')
        .describe('Job mode for the session'),
      max_contextual_job_history: z.number()
        .min(0)
        .max(10)
        .optional()
        .default(10)
        .describe('The maximum number of recent jobs retained as context for the next job'),
      agent_id: z.enum(['DATA_ANALYSIS_AGENT'])
        .optional()
        .default('DATA_ANALYSIS_AGENT')
        .describe('The ID of the agent')
    },
  • PowerdrillClient helper method that performs the actual POST request to /sessions endpoint to create a session
    async createSession(params: CreateSessionParams) {
      try {
        // Include user_id in the request body if not provided
        const requestBody = {
          ...params,
          user_id: params.user_id || this.config.userId
        };
    
        const response = await this.client.post('/sessions', requestBody);
        return response.data;
      } catch (error: any) {
        console.error('Error creating session:', error.message);
        throw error;
      }
    }
  • TypeScript interface defining parameters for createSession in PowerdrillClient
    export interface CreateSessionParams {
      name: string;
      user_id?: string;
      output_language?: string;
      job_mode?: string;
      max_contextual_job_history?: number;
      agent_id?: 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