How to integrate Ashby MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Ashby Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Ashby to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Ashby agent that can list all candidates for open roles, post a new job opening for engineering, summarize candidates in interview stage, export recent hiring activity to csv through natural language commands.

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

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

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Ashby integration
  • Using Composio's Tool Router to dynamically load and access Ashby 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
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

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

The Ashby MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ashby account. It provides structured and secure access to your recruiting data, so your agent can perform actions like managing job postings, tracking candidate progress, scheduling interviews, and generating hiring reports on your behalf.

  • Automated job posting management: Easily create, update, or close job listings across your organization with direct agent assistance.
  • Candidate pipeline tracking: Have your agent fetch, organize, and update candidate progress through every stage of the hiring process.
  • Interview scheduling and coordination: Let your agent schedule interviews, send calendar invites, and manage interviewer assignments to streamline the process.
  • Data-driven hiring analytics: Generate reports and insights about your hiring funnel, candidate sources, and time-to-hire with a simple agent request.
  • Centralized communication with applicants: Enable your agent to send status updates, feedback, or reminders to candidates, keeping everyone in the loop automatically.

Supported Tools & Triggers

Tools
Add Candidate TagAdd a tag to a candidate.
Change Application SourceChange the source attribution of an application.
Change Application StageMove an application to a different interview stage.
Create ApplicationCreate a new application for a candidate to a specific job.
Create CandidateCreate a new candidate in the system.
Create Candidate TagCreate a new candidate tag.
Create DepartmentCreate a new department.
Create JobCreate a new job opening.
Get API Key InfoRetrieve information about the current API key, including associated organization, user details, and permissions.
Get Application InfoRetrieve detailed information about a specific application by its ID.
Get Candidate InfoRetrieve detailed information about a specific candidate by their ID.
Get Department InfoRetrieve detailed information about a specific department by its ID.
Get Interview InfoRetrieve detailed information about a specific interview type by its ID.
Get Job InfoRetrieve detailed information about a specific job by its ID.
Get Job Posting InfoRetrieve detailed information about a specific job posting by its ID.
Get Location InfoRetrieve detailed information about a specific location by its ID.
Get Opening InfoRetrieve detailed information about a specific opening (job requisition) by its ID.
Get User InfoRetrieve detailed information about a specific user by their ID.
List Application FeedbackRetrieve all feedback submissions for an application.
List Application HistoryRetrieve the complete history of stage transitions for an application.
List ApplicationsRetrieve a list of applications.
List ApprovalsRetrieve a list of approvals (offer approvals, job approvals, etc.
List Archive ReasonsRetrieve a list of all archive reasons.
List Candidate NotesRetrieve all notes for a specific candidate.
List Candidate ProjectsRetrieve all projects associated with a candidate.
List CandidatesRetrieve a list of candidates.
List Candidate TagsRetrieve a list of all candidate tags.
List Close ReasonsRetrieve a list of all close reasons for jobs and openings.
List Communication TemplatesRetrieve a list of all communication templates.
List Custom FieldsRetrieve a list of all custom field definitions.
List DepartmentsRetrieve a list of all departments in the organization.
List Feedback Form DefinitionsRetrieve a list of all feedback form definitions.
List Interviewer PoolsRetrieve a list of all interviewer pools.
List Interview PlansRetrieve a list of interview plans.
List InterviewsRetrieve a list of interviews.
List Interview SchedulesRetrieve a list of interview schedules.
List Interview Stage GroupsRetrieve a list of interview stage groups.
List Job BoardsRetrieve a list of job boards.
List Job PostingsRetrieve a list of job postings.
List JobsRetrieve a list of jobs.
List Job TemplatesRetrieve a list of job templates.
List LocationsRetrieve a list of all locations.
List OffersRetrieve a list of job offers.
List OpeningsRetrieve a list of openings (job requisitions).
List ProjectsRetrieve a list of all projects.
List SourcesRetrieve a list of all candidate sources.
List Source Tracking LinksRetrieve a list of all source tracking links.
List Survey Form DefinitionsRetrieve a list of all survey form definitions.
List UsersRetrieve a list of all users in the organization.
Search CandidatesSearch for candidates by email or name.
Search JobsSearch for jobs by title.
Search ProjectsSearch for projects by title.
Search UsersSearch for users by email or name.
Set Job StatusSet the status of a job (Open, Closed, Draft).
Update ApplicationUpdate custom fields or other properties of an application.
Update CandidateUpdate candidate information such as name, position, company, or school.
Update DepartmentUpdate department information such as name.
Update JobUpdate job details such as title and other properties.
Update Job PostingUpdate job posting details such as title or listing status.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

Prerequisites

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

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.

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

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

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 { experimental_createMCPClient as 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

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: ["ashby"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Ashby 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 Ashby-related tools through the MCP protocol

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 Ashby tools that the agent can use

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 ashby, 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

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("\nšŸ‘‹ 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 Ashby 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 Ashby 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 { experimental_createMCPClient as 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: ["ashby"],
  });

  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 ashby, 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("\nšŸ‘‹ Session ended.");
    process.exit(0);
  });
}

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

Conclusion

You've successfully built a Ashby 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.

How to build Ashby MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Ashby MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ashby MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ashby MCP with Google ADK

LangChain

LangChain

Use Ashby MCP with LangChain

Mastra AI

Mastra AI

Use Ashby MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ashby MCP with LlamaIndex

CrewAI

CrewAI

Use Ashby MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Ashby MCP?

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

Can I use Tool Router MCP with Vercel AI SDK?

Yes, you can. Vercel AI SDK 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 Ashby tools.

Can I manage the permissions and scopes for Ashby while using Tool Router?

Yes, absolutely. You can configure which Ashby 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.

How safe is my data with Composio Tool Router?

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 Ashby data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a callā†—Get started for free