How to integrate Sap successfactors MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Sap successfactors logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Sap successfactors to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Sap successfactors agent that can show your current employee profile details, check your job title and department info, display your contact information in successfactors through natural language commands.

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

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

Also integrate Sap successfactors with

TL;DR

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

The Sap successfactors MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Sap successfactors account. It provides structured and secure access to your HR data, so your agent can retrieve user information, access employee details, and drive workforce automation on your behalf.

  • Current user profile retrieval: Instantly fetch the authenticated user's profile and access up-to-date information about their SAP SuccessFactors account.
  • Employee data access: Allow your agent to securely obtain details about employees, enabling streamlined HR and workforce management workflows.
  • Personalized onboarding support: Use user data to personalize onboarding experiences, helping new hires get up to speed faster with relevant, contextual information.
  • Automated reporting: Enable your agent to pull user-related reports or summaries, supporting HR analytics and decision-making.
  • Seamless integration with enterprise HR processes: Connect user data to other HR tools or workflows, making it easier to automate tasks like leave approvals or performance tracking.

Supported Tools & Triggers

Tools
Approve Calibration SessionFinalize a calibration session that is in the In Progress or Approving status.
Create a Feedback RequestCreate a feedback request in SAP SuccessFactors Continuous Feedback.
Create Learning Activities BulkCreate learning activities and associate them with development goals in bulk (requires third-party LMS integration).
Create OnboardeeCreates a new onboardee in SAP SuccessFactors Onboarding 2.
Create or Update Successor NominationCreate or update a successor nomination for a position or talent pool in succession planning.
Delete NominationDelete a nomination for a position or talent pool in succession planning.
Get Application InterviewRetrieves interview information related to job applications from Interview Central.
Get Background EducationTool to retrieve background education records for employees from SAP SuccessFactors.
Get Background MobilityRetrieves mobility background records showing employee willingness to relocate.
Get Calibration Session By IDGet a specific calibration session by session ID.
Get Calibration SessionsQuery all the calibration sessions that a user can access.
Get Calibration Subject By IDQuery a specific subject's competency ratings and ratings within a calibration session.
Get Calibration Subject RatingsQuery a subject's ratings, competency ratings, and comments by using session ID.
Get CDP Learning MetadataGet metadata for Career Development Planning Learning service.
Get Current UserRetrieves the currently authenticated user's information from SAP SuccessFactors.
Get Custom MDF ObjectTool to retrieve custom MDF (Metadata Framework) objects from SAP SuccessFactors.
Get Employee Employment TerminationRetrieves employee termination information records from SAP SuccessFactors.
Get Employee TimeRetrieves employee time entries including time off records from SAP SuccessFactors.
Get Employee TimesheetRetrieves employee timesheet records for attendances, overtime, on-call times, and allowances.
Get Non-Recurring Pay ComponentsTool to retrieve non-recurring pay component information including bonuses and one-time payments from SAP SuccessFactors.
Get Recurring Pay ComponentsTool to retrieve recurring pay component information including salary and benefits data from SAP SuccessFactors.
Get Feedback RecordsTool to retrieve continuous feedback records from SAP SuccessFactors Performance and Goals module using OData V4 protocol.
Get FOBusinessUnitRetrieves foundation object business unit records for organizational structure hierarchy.
Get FOCompany RecordsRetrieves foundation object company records from SAP SuccessFactors.
Get Foundation Object Cost CentersRetrieves foundation object cost center records for organizational structure.
Get FODepartment RecordsTool to retrieve foundation object department records from SAP SuccessFactors.
Get Foundation Object Job CodesRetrieves foundation object job code records containing job classification information.
Get Job FunctionsTool to retrieve foundation object job function records for categorizing job roles.
Get Foundation Object LocationTool to retrieve foundation object location records for work locations.
Get FOPayGroupRetrieves foundation object pay group records for compensation and payroll groupings.
Get Form ContentRetrieves performance form content from SAP SuccessFactors.
Get Goal Plan TemplateRetrieves goal plan template information from SAP SuccessFactors.
Get Goals By PlanRetrieves performance goals data using the goal plan ID.
Get Interview Overall AssessmentTool to retrieve overall interview ratings and navigation for assessments from Interview Central.
Get Job ApplicationRetrieves job application records linking candidates to job requisitions.
Get Job Requisition Screening QuestionsTool to retrieve screening questions related to job requisitions from SAP SuccessFactors Recruiting.
Get Job RequisitionTool to retrieve job requisition records from SAP SuccessFactors Recruiting Management.
Get Calibration Session MetadataGet OData metadata for Calibration Session service.
Get Clock In/Out Integration MetadataGet OData metadata for Clock In/Clock Out Integration service.
Get Nomination Service MetadataGet OData metadata for Nomination service.
Get Onboarding Additional Services MetadataGet OData metadata for Onboarding Additional Services.
Get User Entity MetadataRetrieves the OData metadata document for the User entity describing its properties and operations.
Get Onboarding 2.0 ProcessesTool to retrieve Onboarding 2.
Get Pending Feedback RequestsTool to retrieve pending feedback requests or feedback request records from SAP SuccessFactors Continuous Feedback.
Get Personal Information RecordsTool to retrieve personal information records from SAP SuccessFactors Employee Central.
Get Person by IDTool to retrieve person information for an employee by their external person ID.
Get PicklistTool to retrieve picklist definitions from SAP SuccessFactors.
Get Picklist OptionRetrieves picklist option values with localized labels from SAP SuccessFactors.
Get PositionRetrieves position management records from SAP SuccessFactors Employee Central.
Get Talent PoolRetrieves talent pool records including members and nomination details.
Get Temporary Time InformationRetrieves temporary time information records from Time Management module.
Get Time Account SnapshotRetrieves time account snapshot data for leave liability calculation and payroll.
Get Work OrderTool to retrieve work order records for contingent worker management from SAP SuccessFactors.
Give Feedback or Respond to Feedback RequestTool to give performance feedback or respond to a feedback request in SAP SuccessFactors Continuous Performance Management.
List CandidatesTool to retrieve a list of candidates from SAP SuccessFactors.
List Employee Employment RecordsTool to retrieve a list of all employment records from SAP SuccessFactors.
List Person RecordsTool to retrieve a list of person records from SAP SuccessFactors Employee Central.
List UsersTool to retrieve a list of all employee users from SAP SuccessFactors.
Query All Available Clock In/Clock Out GroupsQuery all available clock in/clock out groups.
Query Clock In/Clock Out Group By CodeQuery a clock in/clock out group by code with time event types.
Refresh CDP Learning MetadataRefresh metadata for Career Development Planning Learning service.
Refresh Metadata for Continuous FeedbackRefresh metadata cache for Continuous Feedback service.
Update Calibration Subject RatingsUpdate a subject's competency ratings in a calibration session.
Update Username Post HiringUpdate the internal username of new hires after hiring process is completed from Active Directory.

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

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 { 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: ["sap_successfactors"],
  });

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

  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 sap_successfactors, 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 Sap successfactors 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 Sap successfactors MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Sap successfactors MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Sap successfactors MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Sap successfactors MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Sap successfactors MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Sap successfactors MCP with Claude Cowork

Codex logo

Codex

Use Sap successfactors MCP with Codex

Cursor logo

Cursor

Use Sap successfactors MCP with Cursor

OpenClaw logo

OpenClaw

Use Sap successfactors MCP with OpenClaw

Hermes logo

Hermes

Use Sap successfactors MCP with Hermes

CLI logo

CLI

Use Sap successfactors MCP with CLI

Google ADK logo

Google ADK

Use Sap successfactors MCP with Google ADK

LangChain logo

LangChain

Use Sap successfactors MCP with LangChain

Mastra AI logo

Mastra AI

Use Sap successfactors MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Sap successfactors MCP with LlamaIndex

CrewAI logo

CrewAI

Use Sap successfactors MCP with CrewAI

OpenCode logo

OpenCode

Use Sap successfactors MCP with OpenCode

VS Code logo

VS Code

Use Sap successfactors MCP with VS Code

FAQ

What are the differences in Tool Router MCP and Sap successfactors MCP?

With a standalone Sap successfactors MCP server, the agents and LLMs can only access a fixed set of Sap successfactors tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Sap successfactors 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 v6?

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 Sap successfactors tools.

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

Yes, absolutely. You can configure which Sap successfactors 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 Sap successfactors data and credentials are handled as safely as possible.

Used by agents from

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

Get started for freeGet a demo↗