Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the Jentic MCP server

Vendor MCP
Open markdown

The Jentic MCP connector routes your AI agent's tool calls to Jentic's own MCP server through Scalekit. Each user signs in to Jentic once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 4 tools.

Tools
4
What they doRead · write · destructive
3 · 0 · 13 read0 write1 destructive
Users sign in with
OAuth app
Scalekit's or your own

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv

  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. Create the Jentic MCP connection

    In AgentKit > Connections, create a Jentic MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

    Scalekit credentials are available for Jentic MCP server, so you don't need to register an OAuth app.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENVIRONMENT_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'jenticmcp'
    const identifier = 'user_123'
    

    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Jentic MCP:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'jenticmcp_list_credentials',
      toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • jenticmcp_list_credentialsList all API credentials the authenticated agent has access to, showing which APIs are available to use.Read-only

    List Credentials

    List all API credentials the authenticated agent has access to, showing which APIs are available to use.

    Inputs

    This tool takes no inputs.

  • jenticmcp_load_execution_infoRetrieve detailed information about a specific action before running it, including required inputs and parameters.Read-only

    Load Execution Info

    Retrieve detailed information about a specific action before running it, including required inputs and parameters.

    Inputs

    requestobjectrequired
    No description.
  • jenticmcp_search_apisSearch for available API actions based on a natural language description of what the user wants to do.Read-only

    Search Apis

    Search for available API actions based on a natural language description of what the user wants to do.

    Inputs

    requestobjectrequired
    No description.
  • jenticmcp_executeExecute a specific API action using provided parameters, including any required inputs for the operation.Destructive

    Execute

    Execute a specific API action using provided parameters, including any required inputs for the operation.

    Inputs

    paramsobjectrequired
    No description.
All 92 in Developer Tools