How to integrate Workable MCP with Vercel AI SDK v6

This guide walks you through connecting Workable to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Workable agent that can list all candidates for open roles, show scheduled interviews for this week, fetch all current job postings through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Workable account through Composio's Workable MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Workable logoWorkable
Oauth2Api Key

Workable is an all-in-one HR software platform that streamlines hiring, employee management, and payroll. It helps teams simplify recruiting, onboarding, and staff operations in one place.

37 Tools

Introduction

This guide walks you through connecting Workable to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Workable agent that can list all candidates for open roles, show scheduled interviews for this week, fetch all current job postings through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Workable account through Composio's Workable MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Workable with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Workable integration
  • Using Composio's Tool Router to dynamically load and access Workable tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Workable MCP server, and what's possible with it?

The Workable MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Workable account. It provides structured and secure access to your hiring and HR data, so your agent can perform actions like listing jobs, managing candidates, retrieving background check info, and organizing departments on your behalf.

  • Comprehensive candidate management: Instantly retrieve and aggregate candidate data across all jobs, making it easy for your agent to analyze talent pipelines, track applicants, and surface top candidates.
  • Job and account insights: Let your agent list all open roles, access job details, and pull account-wide information to keep your hiring team up-to-date and organized.
  • Automated event and interview scheduling: Fetch all scheduled events, interviews, and meetings so your agent can help coordinate calendars and ensure everyone’s on the same page.
  • Background check integration: Retrieve available background check providers and packages, enabling your agent to streamline compliance and onboarding workflows.
  • Team and department organization: List or delete departments, fetch member rosters, and manage legal entities—helping your agent automate org chart updates and keep your HR records tidy.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["workable"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Workable tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Workable-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Workable tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to workable, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Workable tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Workable and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["workable"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to workable, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Workable agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Workable action and event your agent gets out of the box.

Create Employee

Tool to create an employee in your Workable account.

Delete Department

Tool to delete a department.

Delete Subscription

Tool to unsubscribe from an event by deleting a webhook subscription.

Get Account

Tool to return the specified account.

Get Accounts

Retrieves all Workable accounts (organizations) accessible to the authenticated user.

Get Background Check Packages

Tool to retrieve a list of available background check packages from a specified provider.

Get Background Check Providers

Retrieves a list of background check providers integrated with your Workable account.

Get Candidates

Retrieve a list of candidates across all jobs in the organization.

Get Employee

Tool to retrieve detailed information for a specific employee by ID.

Get Events

Retrieve a collection of scheduled events (calls, interviews, meetings) from the Workable account.

Get Jobs

Retrieves a paginated list of jobs from your Workable account.

Get Legal Entities

Tool to retrieve a collection of your account legal entities.

Get Members

Retrieve a paginated list of Workable account members with their roles and permissions.

Get recruiters

Retrieves external recruiters from your Workable account.

Get Requisitions

Tool to retrieve a collection of requisitions in the account.

Get Stages

Tool to retrieve a collection of your recruitment pipeline stages.

Get Subscriptions

Retrieves all webhook subscriptions configured in your Workable account.

List Custom Attributes

Tool to retrieve all custom attributes configured in the Workable account.

List Departments

Tool to retrieve all departments from your Workable account.

List Disqualification Reasons

Tool to retrieve a collection of account's disqualification reasons.

List Employee Fields

Tool to retrieve a collection of your account's employee field definitions.

List Employees

Tool to retrieve a collection of account employees.

List Permission Sets

Tool to retrieve a collection of your account permission sets.

List Public Jobs

Tool to return a collection of public jobs for an account.

List Public Locations

Tool to retrieve a collection of locations where a Workable account has public job postings.

List Time Off Balances

Retrieves all time off balances for an employee across all time off categories.

List Time Off Categories

Tool to retrieve all time off categories configured for your account.

List Work Schedules

Tool to retrieve a collection of work schedules configured in your Workable account.

Update Background Check Status

Updates the status and results of an existing background check in a candidate's timeline.

Merge Department

Tool to merge a department into another.

Create Department

Tool to create a department in your account.

Enable Member

Enable (restore) a deactivated Workable account member to active status.

Invite Member

Tool to invite a member to your Workable account.

Update Department

Tool to update an existing department in your account.

Update Member

Updates a Workable account member's details including roles, name, headline, email, and collaboration rules.

Update Employee

Tool to update an existing employee in Workable.

Upload Employee Documents

Tool to upload a list of documents for a specific employee.

FAQ

Frequently asked questions

With a standalone Workable MCP server, the agents and LLMs can only access a fixed set of Workable tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Workable and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Workable tools.

Yes, absolutely. You can configure which Workable scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Workable data and credentials are handled as safely as possible.

Start with Workable.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Workable tool your agent needs.Free to start.

Start building