SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Lever MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Lever MCP. List all open job postings, get candidate details by email, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Lever logoLever
Api KeyOauth2

Lever is an applicant tracking system that blends sourcing, CRM, and analytics for recruiting. It helps companies scale hiring with collaborative workflows and actionable insights.

64 Tools

Introduction

This guide walks you through connecting Lever to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Lever agent that can create opportunities, schedule interviews, add notes and tags, manage requisitions, and list postings and offers through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Lever with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Lever integration
  • Using Composio's Tool Router to dynamically load and access Lever 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 Lever MCP server, and what's possible with it?

The Lever MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Lever account. It provides structured and secure access to your recruiting pipeline, so your agent can perform actions like managing candidates, scheduling interviews, updating requisitions, tracking offers, and listing hiring stages on your behalf.

  • End-to-end candidate management: Let your agent add, update, or tag candidates in your hiring process seamlessly.
  • Automated interview scheduling: Have the agent create, modify, or cancel interviews and retrieve interview details to streamline the process.
  • Job posting and requisition updates: Direct your agent to list job postings, update existing requisitions, or close filled roles instantly.
  • Offer and feedback tracking: Enable your agent to list offers, track acceptance rates, and collect structured feedback from interviewers.
  • Recruiting analytics and reporting: Ask the agent to list pipeline opportunities, recruitment sources, and candidate tags, helping you make data-driven hiring decisions.

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: ["lever"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Lever 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 Lever-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 Lever 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 lever, 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 Lever 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 Lever 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: ["lever"],
  });

  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 lever, 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 Lever 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 Lever action and event your agent gets out of the box.

Add Opportunity Links

Tool to add links to a contact associated with an opportunity.

Add Opportunity Sources

Tool to add sources to an opportunity.

Add Opportunity Tags

Tool to add tags to an opportunity.

Create Form Submission

Tool to create a completed profile form submission for a candidate's opportunity profile.

Create Form Template

Tool to create a profile form template for an account.

Create Interview

Tool to create an interview on an externally-managed panel in Lever.

Create Note

Tool to create a note on an opportunity profile or add a threaded comment to an existing note.

Create Opportunity

Tool to create a new candidate opportunity in Lever.

Create Panel

Tool to create a new interview panel for an opportunity.

Create Requisition

Tool to create a new requisition in Lever for tracking hiring needs.

Create Requisition Field

Tool to create a custom requisition field schema for use across requisitions.

Create Requisition Field Option

Add new options to a Lever dropdown requisition field without replacing its existing choices.

Upload File

Upload a file temporarily to Lever for use in posting applications.

Create User

Tool to create a new user in the Lever system.

Deactivate User

Tool to deactivate a user in the Lever system.

Delete Form Template

Tool to delete a profile form template from account.

Delete Interview

Delete an interview from an opportunity's externally managed panel on behalf of a user.

Delete Note

Tool to delete a note on an opportunity.

Delete Panel

Tool to delete a panel from an opportunity.

Delete Requisition

Delete a requisition from a Lever account by its ID.

Delete Requisition Field

Delete a requisition field from the account.

Delete Requisition Field Option

Tool to remove specific options from a dropdown requisition field.

Download File

Tool to download a file associated with an opportunity.

Get File Metadata

Tool to retrieve metadata for a single file on an opportunity.

Get Form

Tool to retrieve a specific profile form for an opportunity.

Get Form Template

Tool to retrieve a single form template by unique identifier.

Get Interview

Tool to retrieve a single interview for an opportunity.

Get Note

Tool to retrieve a single note for an opportunity.

Get Opportunity

Tool to retrieve detailed information about a single opportunity.

Get Panel

Tool to retrieve a single interview panel for an opportunity.

Get Requisition

Retrieve a single requisition by ID, including hiring status and headcount.

Get Requisition Field

Tool to retrieve detailed information about a single custom requisition field by ID.

Get Stage

Tool to retrieve detailed information about a single stage by its UUID.

Get User

Tool to retrieve detailed information about a single user by their UUID.

List Opportunity Files

Tool to list all files on an opportunity.

List Forms

Tool to list all profile forms for an opportunity.

List Form Templates

Tool to list all active form templates.

List Interviews

List a page of interviews for an opportunity, with pagination controls for additional results.

List Notes

List notes on a Lever opportunity profile using its opportunity ID.

List Offers

Tool to list offers for an opportunity.

List Opportunities

List a page of hiring pipeline opportunities with optional filters for contact, posting, stage, tags, time ranges, and other criteria.

List Panels

Tool to list all interview panels for an opportunity.

List Postings

List job postings with optional filters for state, team, department, location, commitment, level, tag, or update timestamp.

List Referrals

Tool to list all referrals for an opportunity.

List Requisition Fields

List requisition field schemas in a Lever account, with optional filtering by field type.

List Requisitions

Tool to list all requisitions with filtering and pagination.

List Opportunity Resumes

List resume records for a specified Lever opportunity, including available file metadata and parsed resume data.

List Sources

Tool to list all recruitment sources in your Lever account.

List Stages

Tool to retrieve all pipeline stages in your Lever account.

List Tags

Tool to list all tags in your Lever account.

List Users

Tool to retrieve all active users in your Lever account with optional filters.

Reactivate User

Tool to reactivate a previously deactivated user in the Lever system.

Remove Contact Links by Opportunity

Tool to remove links from a contact associated with an opportunity.

Remove Opportunity Sources

Tool to remove sources from an opportunity.

Remove Opportunity Tags

Tool to remove tags from an opportunity.

Update Form Template

Tool to update an existing profile form template.

Update Interview

Update an interview on an externally managed panel.

Update Note

Update an API-created note on an opportunity profile.

Update Panel

Update an externally managed interview panel for an opportunity, including its interviews and other panel details.

Update Requisition

Update an existing requisition's details, such as name, headcount and status.

Update Requisition Field

Tool to update an existing requisition field in Lever.

Update Requisition Field Option

Update the display text of one or more existing options in a Lever dropdown requisition field.

Update User

Tool to update an existing user in the Lever system.

Upload File to Opportunity

Tool to upload a file permanently to an opportunity.

FRAMEWORKS

How to build Lever MCP Agent with another framework

Claude Code logo

Claude Code

Use Lever MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Lever MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Lever MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Lever MCP with Claude Agent SDK

Codex logo

Codex

Use Lever MCP with Codex

OpenClaw logo

OpenClaw

Use Lever MCP with OpenClaw

Hermes logo

Hermes

Use Lever MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Lever MCP with Atomic Agent

Google ADK logo

Google ADK

Use Lever MCP with Google ADK

LangChain logo

LangChain

Use Lever MCP with LangChain

Mastra AI logo

Mastra AI

Use Lever MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Lever MCP with LlamaIndex

CrewAI logo

CrewAI

Use Lever MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Lever MCP with Pydantic AI

AutoGen logo

AutoGen

Use Lever MCP with AutoGen

FAQ

Frequently asked questions

Start with Lever.It takes 30 seconds.

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

Start building