IGPT MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'igptmcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize IGPT MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'igptmcp_search',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "igptmcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize IGPT MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="igptmcp_search",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Search records — Search connected datasources which include documents and messages
• Ask records — Sends user question to backend and returns answer based on connected datasources which include documents and messages

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

igptmcp_ask#Sends user question to backend and returns answer based on connected datasources which include documents and messages2 params▾

Sends user question to backend and returns answer based on connected datasources which include documents and messages

NameTypeRequiredDescription

inputstringrequiredUser input question

output_formatstringoptionalOutput format. Use "json" for a automatic generic object, or provide a JSON Schema to enforce a specific output structure ex:{"schema":{"type":"object"}}

igptmcp_search#Search connected datasources which include documents and messages3 params▾

Search connected datasources which include documents and messages

NameTypeRequiredDescription

date_fromstringoptionalOptional lower bound (inclusive) date for filtering results by their timestamp, date only (e.g. 2025-01-01). Only set this when the user explicitly specifies a concrete start date or range.

date_tostringoptionalOptional upper bound (inclusive) date for filtering results by their timestamp, date only (e.g. 2025-01-01). Only set this when the user explicitly specifies a concrete start date or range.

querystringoptionalOptional search query. When provided, the tool performs a hybrid search (semantic + full-text). When omitted or empty, the tool returns results sorted in descending ordered by recency.