SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Yandex MCP with Mastra AI

Connect Mastra AI to Yandex MCP. Find walking route from red square to gorky park, look up a business by address in moscow, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Yandex logoYandex
Oauth2

Yandex is a leading Russian internet services provider offering search, email, maps, and more. It's known for robust email, navigation, and web-based solutions tailored for Russian-speaking users.

21 Tools

Introduction

This guide walks you through connecting Yandex to Mastra AI using the Composio tool router. By the end, you'll have a working Yandex agent that can reverse geocode coordinates, generate routes, search organizations, browse Yandex Music playlists, and fetch public Yandex Disk files through natural language commands.

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

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

Also integrate Yandex with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKLlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Set up your environment so Mastra, OpenAI, and Composio work together
  • Create a Tool Router session in Composio that exposes Yandex tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Yandex tool definitions and attach them as a toolset
  • Build a Mastra agent that can reason, call tools, and return structured results
  • Run an interactive CLI where you can chat with your Yandex agent

What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.

Key features include:

  • MCP Client: Built-in support for Model Context Protocol servers
  • Toolsets: Organize tools into logical groups
  • Step Callbacks: Monitor and debug agent execution
  • OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

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

The Yandex MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Yandex account. It provides structured and secure access to Yandex search, maps, and business information, so your agent can perform actions like business lookup, reverse geocoding, detailed route planning, and retrieving map tiles on your behalf.

  • Business and organization search: Instantly find businesses or organizations by name, address, or tax ID—perfect for regional lookups and company discovery.
  • Reverse geocoding for precise locations: Translate latitude and longitude into street addresses or place names using Yandex Maps, making it easy to identify places from coordinates.
  • Detailed route generation: Let your agent plan step-by-step driving, walking, or public transportation routes between two points, complete with directions and travel options.
  • Custom map tile retrieval: Fetch specific map tile images by their coordinates and zoom level, enabling custom visualizations or interactive map experiences.

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 starting, make sure you have:
  • Node.js 18 or higher
  • A Composio account with an active API key
  • An OpenAI API key
  • Basic familiarity with TypeScript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key.
  • You need credits or a connected billing setup to use the models.
  • Store the key somewhere safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Yandex through MCP.
3

Install dependencies

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

Install the required packages.

What's happening:

  • @composio/core is the Composio SDK for creating MCP sessions
  • @mastra/core provides the Agent class
  • @mastra/mcp is Mastra's MCP client
  • @ai-sdk/openai is the model wrapper for OpenAI
  • dotenv loads environment variables from .env
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio
  • COMPOSIO_USER_ID tells Composio which user this session belongs to
  • OPENAI_API_KEY lets the Mastra agent call OpenAI models
5

Import libraries and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

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

if (!openaiAPIKey) 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 as string,
});
What's happening:
  • dotenv/config auto loads your .env so process.env.* is available
  • openai gives you a Mastra compatible model wrapper
  • Agent is the Mastra agent that will call tools and produce answers
  • MCPClient connects Mastra to your Composio MCP server
  • Composio is used to create a Tool Router session
6

Create a Tool Router session for Yandex

typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["yandex"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Yandex MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "yandex" for Yandex access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to
7

Configure Mastra MCP client and fetch tools

typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
What's happening:
  • MCPClient takes an id for this client and a list of MCP servers
  • The headers property includes the x-api-key for authentication
  • getTools fetches the tool definitions exposed by the Yandex toolkit
8

Create the Mastra agent

typescript
const agent = new Agent({
    name: "yandex-mastra-agent",
    instructions: "You are an AI agent with Yandex tools via Composio.",
    model: "openai/gpt-5",
  });
What's happening:
  • Agent is the core Mastra agent
  • name is just an identifier for logging and debugging
  • instructions guide the agent to use tools instead of only answering in natural language
  • model uses openai("gpt-5") to configure the underlying LLM
9

Set up interactive chat interface

typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\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({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        yandex: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

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

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Yandex toolsets
  • maxSteps limits how many tool calls the agent can take in a single run
  • onStepFinish is a hook that prints intermediate steps for debugging

Complete Code

Here's the complete code to get you started with Yandex and Mastra AI:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

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

if (!openaiAPIKey) 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 as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["yandex"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      yandex: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "yandex-mastra-agent",
    instructions: "You are an AI agent with Yandex tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

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

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { yandex: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();

Conclusion

You've built a Mastra AI agent that can interact with Yandex through Composio's Tool Router. You can extend this further by:
  • Adding other toolkits like Gmail, Slack, or GitHub
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows
TOOLS

Supported Tools

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

Reverse Geocode Coordinates

Tool to convert geographic coordinates to a human-readable address (reverse geocoding).

Get Account Experiments

Tool to retrieve Yandex Music account experimental features and A/B testing flags.

Get Account Status

Tool to retrieve Yandex Music account status and permissions.

Get Music Genres

Tool to retrieve the list of music genres from Yandex Music.

Get Permission Alerts

Tool to retrieve permission alerts and notifications from Yandex Music API.

Get Playlists by Tag

Tool to retrieve playlist IDs associated with a specific tag.

Get Public Resource Metadata

Tool to retrieve metadata for a public file or folder on Yandex Disk.

Get Public Resource Download Link

Tool to get a direct download link for a publicly shared Yandex Disk resource.

Get Rotor Account Status

Tool to retrieve authenticated user's rotor account status with supplementary fields.

Get Rotor Stations Dashboard

Tool to retrieve recommended radio stations for the current user.

Get Yandex Music Settings

Tool to retrieve Yandex Music settings including available purchase products and payment configuration.

Get Yandex Music Stations List

Tool to retrieve all radio stations with user settings from Yandex Music.

Get Track Download Info

Retrieve available download variants for a Yandex Music track, including codecs, bitrates and download-info URLs.

List Filters

Tool to retrieve all filters configured for a Yandex Metrica counter.

List Goals

Tool to retrieve all goals configured for a Yandex Metrica counter.

List Counter Grants

Tool to retrieve the list of permissions (grants) for a Yandex Metrica counter.

List Log Requests

Tool to retrieve a list of log requests for a Yandex Metrica counter.

List Storage Buckets

Tool to list all Yandex Object Storage buckets owned by the authenticated user.

Organization Search

Tool to find businesses and organizations by name, address, or TIN.

Generate detailed route

Generate a detailed route between specified geographic points for driving, truck, walking, public transport, bicycle, or scooter travel.

Yandex Tiles API

Fetch an individual Yandex map tile image by x/y coordinates and zoom level for custom map rendering.

FRAMEWORKS

How to build Yandex MCP Agent with another framework

Claude Code logo

Claude Code

Use Yandex MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Yandex MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Yandex MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Yandex MCP with Claude Agent SDK

Codex logo

Codex

Use Yandex MCP with Codex

OpenClaw logo

OpenClaw

Use Yandex MCP with OpenClaw

Hermes logo

Hermes

Use Yandex MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Yandex MCP with Atomic Agent

Google ADK logo

Google ADK

Use Yandex MCP with Google ADK

LangChain logo

LangChain

Use Yandex MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Yandex MCP with Vercel AI SDK

LlamaIndex logo

LlamaIndex

Use Yandex MCP with LlamaIndex

CrewAI logo

CrewAI

Use Yandex MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Yandex MCP with Pydantic AI

AutoGen logo

AutoGen

Use Yandex MCP with AutoGen

FAQ

Frequently asked questions

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

Yes, you can. Mastra AI 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 Yandex tools.

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

Start with Yandex.It takes 30 seconds.

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

Start building