How to integrate Dadata ru MCP with Vercel AI SDK v6

This guide walks you through connecting Dadata ru to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Dadata ru agent that can clean and standardize this russian address, validate and parse a user's full name, check if this passport number is valid through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Dadata ru account through Composio's Dadata ru MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Dadata ru logoDadata ru
Api Key

Dadata ru is a data validation and enrichment API for Russian addresses, companies, and personal data. It helps automate data entry, reduce errors, and standardize records across your workflows.

63 Tools

Introduction

This guide walks you through connecting Dadata ru to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Dadata ru agent that can clean and standardize this russian address, validate and parse a user's full name, check if this passport number is valid through natural language commands.

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

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

Also integrate Dadata ru with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

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

The Dadata ru MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Dadata ru account. It provides structured and secure access to DaData’s powerful data validation and enrichment APIs, so your agent can perform actions like standardizing addresses, cleaning contact details, parsing names, and retrieving company or bank information on your behalf.

  • Accurate address standardization and parsing: Instantly clean and structure messy Russian addresses or retrieve address details using identifiers like cadastral numbers or FIAS IDs.
  • Email, phone, and passport validation: Let your agent validate and clean raw email addresses, phone numbers, or Russian passport numbers to ensure your data is correct and safe to use.
  • Full name parsing and gender detection: Automatically break down full names (FIO), identify gender, and get grammatical declensions to power advanced personalization or document processing.
  • Vehicle and car brand data enrichment: Extract structured vehicle details and fetch comprehensive car brand information by code for registration or verification workflows.
  • Bank information retrieval: Quickly find complete bank details by BIC, SWIFT, INN, or registration numbers, streamlining financial processes and verifications.

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: ["dadata_ru"],
  });

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

  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 dadata_ru, 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 Dadata ru 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 Dadata ru action and event your agent gets out of the box.

Clean Address

Clean and standardize a Russian postal address.

Clean Birthdate

Standardize and validate birthdate strings.

Clean Email

Standardize and validate an email address.

Clean Name (FIO)

Tool to standardize and parse full names (FIO), detect gender, and return grammatical cases.

Clean Passport

Tool to validate a Russian passport number against the official registry.

Clean Phone

Tool to standardize and validate phone numbers.

Clean Composite Record

Tool to standardize composite records with multiple contact data fields in a single request.

Clean Vehicle

Standardize and recognize vehicle make/model from free-form text input.

Find Address

Retrieve full Russian address details by FIAS ID, KLADR code, or cadastral number.

Find Bank

Tool to find bank by BIC, SWIFT, INN, or registration number.

Find Car Brand

Find car brand details by identifier.

Find Company By Email

Find companies by corporate email address domain.

Find Country

Tool to find country details by ISO or numeric code.

Find Court by ID

Find court by ID or code.

Find Currency

Tool to find currency details by ISO 4217 code.

Find Delivery City IDs

Retrieves delivery service city identifiers (CDEK, Boxberry, DPD) for a given Russian city by KLADR code or FIAS ID.

Find Address by FIAS ID

Find address by FIAS ID from the Federal Information Address System (FIAS/GAR).

Find FMS Unit

Look up Russian passport issuing authority (FMS unit) by subdivision code.

Find FNS Unit by Code

Find Russian tax inspection (FNS unit) by exact code or INN.

Find FTS Unit

Find a Russian Federal Customs Service (FTS) unit by its 8-digit code.

Find Medical Position By ID

Tool to find medical position by ID code.

Find MKTU

Look up MKTU (International Classification of Goods and Services/Nice Classification) items by their numeric code.

Find OKPD2 by ID

Look up OKPD2 (Russian Classification of Products by Economic Activity) entries by their exact code.

Find OKPDTR Position

Find job position by OKPDTR code.

Find OKPDTR Profession

Tool to find profession details by OKPDTR code.

Find Territory by OKTMO

Find Russian municipal territory by OKTMO code.

Find OKVED2

Look up OKVED2 (Russian Classification of Economic Activities) entries by their exact code.

Find Company or Entrepreneur

Find company or individual entrepreneur details by INN or OGRN from the Russian Federal Tax Service registry.

Find Belarus Party by UNP

Tool to find a Belarusian company or entrepreneur by UNP.

Find Kazakhstan Company by BIN

Look up Kazakhstan company or entrepreneur details by BIN (Business Identification Number).

Find Postal Office

Find Russian postal office details by postal code (index).

Find Postal Unit By ID

Find postal unit by postal code.

Geolocate Address

Tool to find nearest addresses by geographic coordinates.

Geolocate Postal Unit

Tool to find nearest postal units by geographic coordinates.

Get Profile Balance

Tool to retrieve current DaData account balance.

Get Profile Statistics

Tool to get daily aggregated usage statistics per DaData API service.

Get Reference Versions

Tool to retrieve the last update dates for DaData reference datasets (FIAS, EGRUL, banks, etc.

IP Locate Address

Geolocate a Russian IP address to determine its city/region.

Suggest Address

Tool to autocomplete and suggest addresses.

Suggest Bank

Tool to autocomplete and suggest banks by partial details.

Suggest Car Brand

Tool to suggest car brands.

Suggest Country

Tool to suggest countries based on user input.

Suggest Court

Tool to suggest Russian courts by name or location.

Suggest Currency

Tool to suggest currencies by ISO 4217 code or name.

Suggest Email

Tool to autocomplete and suggest email addresses.

Suggest FIAS Address

Tool to suggest addresses from FIAS/GAR database.

Suggest FMS Unit

Tool to autocomplete and suggest passport issuing authorities.

Suggest FNS Unit

Tool to suggest Russian tax inspection units by partial name or code.

Suggest FTS Unit

Tool to autocomplete and suggest Russian customs (FTS) units.

Suggest Medical Position

Tool to autocomplete and suggest medical positions and specialties.

Suggest Metro

Tool to suggest metro stations.

Suggest MKTU

Autocomplete and search for MKTU (Nice Classification) codes used for trademark registration.

Suggest Name

Tool to autocomplete and suggest full names (FIO).

Suggest OKPD2

Tool to autocomplete and suggest Russian product classification codes (OKPD2).

Suggest OKPDTR Position

Tool to autocomplete and suggest Russian job positions from OKPDTR classifier.

Suggest OKPDTR Profession

Tool to autocomplete and suggest professions from OKPDTR classifier.

Suggest OKTMO

Suggest Russian municipal territory codes (OKTMO) by code prefix or partial name.

Suggest OKVED2

Tool to suggest OKVED2 codes by text query.

Suggest Party

Tool to autocomplete and suggest Russian companies or entrepreneurs.

Suggest Belarus Party

Tool to autocomplete and suggest Belarusian companies or entrepreneurs.

Suggest Kazakhstan Company

Tool to autocomplete and suggest Kazakhstan companies or entrepreneurs.

Suggest Postal Office

Suggests Russian Post offices by postal code or address.

Suggest Postal Unit

Suggests Russian Post offices (Почта России) by postal code or address.

FRAMEWORKS

How to build Dadata ru MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Dadata ru MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Dadata ru MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Dadata ru MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Dadata ru MCP with Claude Cowork

Codex logo

Codex

Use Dadata ru MCP with Codex

OpenClaw logo

OpenClaw

Use Dadata ru MCP with OpenClaw

Hermes logo

Hermes

Use Dadata ru MCP with Hermes

CLI logo

CLI

Use Dadata ru MCP with CLI

Google ADK logo

Google ADK

Use Dadata ru MCP with Google ADK

LangChain logo

LangChain

Use Dadata ru MCP with LangChain

Mastra AI logo

Mastra AI

Use Dadata ru MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Dadata ru MCP with LlamaIndex

CrewAI logo

CrewAI

Use Dadata ru MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Dadata ru.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies