# How to integrate Yandex MCP with CrewAI ```json { "title": "How to integrate Yandex MCP with CrewAI", "toolkit": "Yandex", "toolkit_slug": "yandex", "framework": "CrewAI", "framework_slug": "crew-ai", "url": "https://composio.dev/toolkits/yandex/framework/crew-ai", "markdown_url": "https://composio.dev/toolkits/yandex/framework/crew-ai.md", "updated_at": "2026-05-12T10:30:52.789Z" } ``` ## Introduction This guide walks you through connecting Yandex to CrewAI using the Composio tool router. By the end, you'll have a working Yandex agent that can find walking route from red square to gorky park, look up a business by address in moscow, get map tiles for downtown saint petersburg through natural language commands. This guide will help you understand how to give your CrewAI 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 - [OpenAI Agents SDK](https://composio.dev/toolkits/yandex/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/yandex/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/yandex/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/yandex/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/yandex/framework/codex) - [OpenClaw](https://composio.dev/toolkits/yandex/framework/openclaw) - [Hermes](https://composio.dev/toolkits/yandex/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/yandex/framework/cli) - [Google ADK](https://composio.dev/toolkits/yandex/framework/google-adk) - [LangChain](https://composio.dev/toolkits/yandex/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/yandex/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/yandex/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/yandex/framework/llama-index) ## TL;DR Here's what you'll learn: - Get a Composio API key and configure your Yandex connection - Set up CrewAI with an MCP enabled agent - Create a Tool Router session or standalone MCP server for Yandex - Build a conversational loop where your agent can execute Yandex operations ## What is CrewAI? CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews. Key features include: - Agent Roles: Define specialized agents with specific goals and backstories - Task Management: Create tasks with clear descriptions and expected outputs - Crew Orchestration: Combine agents and tasks into collaborative workflows - MCP Integration: Connect to external tools through Model Context Protocol ## 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. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `YANDEX_GEOCODER_REVERSE` | Reverse Geocode Coordinates | Tool to convert geographic coordinates to a human-readable address (reverse geocoding). Returns address information including street, city, country, and other location details. Use this when you have latitude/longitude coordinates and need to find the corresponding address. | | `YANDEX_GET_ACCOUNT_EXPERIMENTS` | Get Account Experiments | Tool to retrieve Yandex Music account experimental features and A/B testing flags. Use when you need to check which experimental features are enabled for an account. | | `YANDEX_GET_ACCOUNT_STATUS` | Get Account Status | Tool to retrieve Yandex Music account status and permissions. Use when you need to check account availability, region, subscription status, and granted permissions. | | `YANDEX_GET_GENRES` | Get Music Genres | Tool to retrieve the list of music genres from Yandex Music. Use when you need to get available music genres for browsing or categorization. | | `YANDEX_GET_PERMISSION_ALERTS` | Get Permission Alerts | Tool to retrieve permission alerts and notifications from Yandex Music API. Use this to check for system notifications about subscription status, permissions, or other user alerts. | | `YANDEX_GET_PLAYLISTS_IDS_BY_TAG` | Get Playlists by Tag | Tool to retrieve playlist IDs associated with a specific tag. Use when you need to find playlists categorized under a tag like 'rock', 'pop', or 'jazz'. | | `YANDEX_GET_PUBLIC_RESOURCE` | Get Public Resource Metadata | Tool to retrieve metadata for a public file or folder on Yandex Disk. Use when you need to get information about publicly shared resources including their properties, nested items, and download URLs. | | `YANDEX_GET_PUBLIC_RESOURCE_DOWNLOAD_LINK` | Get Public Resource Download Link | Tool to get a direct download link for a publicly shared Yandex Disk resource. Use when you need to download a file or folder that has been shared publicly. | | `YANDEX_GET_ROTOR_ACCOUNT_STATUS` | Get Rotor Account Status | Tool to retrieve authenticated user's rotor account status with supplementary fields. Use to check user subscription status, permissions, and radio-specific settings like skips_per_hour. | | `YANDEX_GET_ROTOR_STATIONS_DASHBOARD` | Get Rotor Stations Dashboard | Tool to retrieve recommended radio stations for the current user. Use when you need to get the user's personalized station dashboard. | | `YANDEX_GET_SETTINGS` | Get Yandex Music Settings | Tool to retrieve Yandex Music settings including available purchase products and payment configuration. Use when you need to check available subscription options, pricing, or payment methods. | | `YANDEX_GET_STATIONS_LIST` | Get Yandex Music Stations List | Tool to retrieve all radio stations with user settings from Yandex Music. Use when you need to get the list of available radio stations and their configurations. | | `YANDEX_GET_TRACK_DOWNLOAD_INFO` | Get Track Download Info | Tool to retrieve available download options for a Yandex Music track. Returns a list of download variants with different codecs (MP3/AAC) and bitrates. Use this when you need to get download links for a specific track ID. | | `YANDEX_LIST_FILTERS` | List Filters | Tool to retrieve all filters configured for a Yandex Metrica counter. Use when you need to view existing filters for data filtering or analysis. | | `YANDEX_LIST_GOALS` | List Goals | Tool to retrieve all goals configured for a Yandex Metrica counter. Use when you need to list or inspect goals for analytics tracking. | | `YANDEX_LIST_GRANTS` | List Counter Grants | Tool to retrieve the list of permissions (grants) for a Yandex Metrica counter. Use when you need to check who has access to view or manage a counter and their permission levels. | | `YANDEX_LIST_LOG_REQUESTS` | List Log Requests | Tool to retrieve a list of log requests for a Yandex Metrica counter. Use when you need to view all log requests associated with a specific counter ID. | | `YANDEX_LIST_STORAGE_BUCKETS` | List Storage Buckets | Tool to list all Yandex Object Storage buckets owned by the authenticated user. Use when you need to retrieve a list of available S3-compatible storage buckets. | | `YANDEX_ORGANIZATION_SEARCH` | Organization Search | Tool to find businesses and organizations by name, address, or TIN. Use when you need to search for companies in a specific region or text query. | | `YANDEX_YANDEX_ROUTE` | Generate detailed route | Tool to generate detailed route for driving, walking, or public transport. Use when planning a route between specified geographic points. | | `YANDEX_YANDEX_TILES` | Yandex Tiles API | Tool to fetch individual map tile images by x/y coordinates and zoom level. Use after calculating tile indices for custom map rendering. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Yandex MCP server is an implementation of the Model Context Protocol that connects your AI agent to Yandex. It provides structured and secure access so your agent can perform Yandex operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before starting, make sure you have: - Python 3.9 or higher - A Composio account and API key - A Yandex connection authorized in Composio - An OpenAI API key for the CrewAI LLM - Basic familiarity with Python ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies **What's happening:** - composio connects your agent to Yandex via MCP - crewai provides Agent, Task, Crew, and LLM primitives - crewai-tools[mcp] includes MCP helpers - python-dotenv loads environment variables from .env ```bash pip install composio crewai crewai-tools[mcp] python-dotenv ``` ### 3. Set up environment variables Create a .env file in your project root. What's happening: - COMPOSIO_API_KEY authenticates with Composio - USER_ID scopes the session to your account - OPENAI_API_KEY lets CrewAI use your chosen OpenAI model ```bash COMPOSIO_API_KEY=your_composio_api_key_here USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key_here ``` ### 4. Import dependencies **What's happening:** - CrewAI classes define agents and tasks, and run the workflow - MCPServerHTTP connects the agent to an MCP endpoint - Composio will give you a short lived Yandex MCP URL ```python import os from composio import Composio from crewai import Agent, Task, Crew from crewai_tools import MCPServerAdapter import dotenv dotenv.load_dotenv() COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set") ``` ### 5. Create a Composio Tool Router session for Yandex **What's happening:** - You create a Yandex only session through Composio - Composio returns an MCP HTTP URL that exposes Yandex tools ```python composio_client = Composio(api_key=COMPOSIO_API_KEY) session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["yandex"]) url = session.mcp.url ``` ### 6. Initialize the MCP Server **What's Happening:** - Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication. - MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format. - Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools. - Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops. - Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries. ```python server_params = { "url": url, "transport": "streamable-http", "headers": {"x-api-key": COMPOSIO_API_KEY}, } with MCPServerAdapter(server_params) as tools: agent = Agent( role="Search Assistant", goal="Help users search the internet effectively", backstory="You are a helpful assistant with access to search tools.", tools=tools, verbose=False, max_iter=10, ) ``` ### 7. Create a CLI Chatloop and define the Crew **What's Happening:** - Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable. - Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean. - Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses. - Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context. - Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response. - Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity. ```python print("Chat started! Type 'exit' or 'quit' to end.\n") conversation_context = "" while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue conversation_context += f"\nUser: {user_input}\n" print("\nAgent is thinking...\n") task = Task( description=( f"Conversation history:\n{conversation_context}\n\n" f"Current request: {user_input}" ), expected_output="A helpful response addressing the user's request", agent=agent, ) crew = Crew(agents=[agent], tasks=[task], verbose=False) result = crew.kickoff() response = str(result) conversation_context += f"Agent: {response}\n" print(f"Agent: {response}\n") ``` ## Complete Code ```python from crewai import Agent, Task, Crew, LLM from crewai_tools import MCPServerAdapter from composio import Composio from dotenv import load_dotenv import os load_dotenv() GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not GOOGLE_API_KEY: raise ValueError("GOOGLE_API_KEY is not set in the environment.") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set in the environment.") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set in the environment.") # Initialize Composio and create a session composio = Composio(api_key=COMPOSIO_API_KEY) session = composio.create( user_id=COMPOSIO_USER_ID, toolkits=["yandex"], ) url = session.mcp.url # Configure LLM llm = LLM( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY"), ) server_params = { "url": url, "transport": "streamable-http", "headers": {"x-api-key": COMPOSIO_API_KEY}, } with MCPServerAdapter(server_params) as tools: agent = Agent( role="Search Assistant", goal="Help users with internet searches", backstory="You are an expert assistant with access to Composio Search tools.", tools=tools, llm=llm, verbose=False, max_iter=10, ) print("Chat started! Type 'exit' or 'quit' to end.\n") conversation_context = "" while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue conversation_context += f"\nUser: {user_input}\n" print("\nAgent is thinking...\n") task = Task( description=( f"Conversation history:\n{conversation_context}\n\n" f"Current request: {user_input}" ), expected_output="A helpful response addressing the user's request", agent=agent, ) crew = Crew(agents=[agent], tasks=[task], verbose=False) result = crew.kickoff() response = str(result) conversation_context += f"Agent: {response}\n" print(f"Agent: {response}\n") ``` ## Conclusion You now have a CrewAI agent connected to Yandex through Composio's Tool Router. The agent can perform Yandex operations through natural language commands. Next steps: - Add role-specific instructions to customize agent behavior - Plug in more toolkits for multi-app workflows - Chain tasks for complex multi-step operations ## How to build Yandex MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/yandex/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/yandex/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/yandex/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/yandex/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/yandex/framework/codex) - [OpenClaw](https://composio.dev/toolkits/yandex/framework/openclaw) - [Hermes](https://composio.dev/toolkits/yandex/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/yandex/framework/cli) - [Google ADK](https://composio.dev/toolkits/yandex/framework/google-adk) - [LangChain](https://composio.dev/toolkits/yandex/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/yandex/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/yandex/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/yandex/framework/llama-index) ## Related Toolkits - [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions. - [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows. - [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations. - [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements. - [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints. - [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots. - [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches. - [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand. - [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance. - [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows. - [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses. - [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research. - [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation. - [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation. - [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses. - [Census bureau](https://composio.dev/toolkits/census_bureau) - Census bureau is the U.S. Census Bureau’s official data API, offering access to nationwide demographic, economic, and geographic statistics. It lets you power your applications and automations with up-to-date, authoritative U.S. data. - [Codereadr](https://composio.dev/toolkits/codereadr) - Codereadr is a mobile platform for barcode scanning and data collection. It helps businesses securely capture, validate, and report field data with ease. - [Coinmarketcap](https://composio.dev/toolkits/coinmarketcap) - Coinmarketcap is a leading cryptocurrency data platform offering real-time and historical market data on digital coins and exchanges. It empowers users to track prices, volumes, and trends for smarter crypto decisions. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Yandex MCP? 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. ### Can I use Tool Router MCP with CrewAI? Yes, you can. CrewAI 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. ### Can I manage the permissions and scopes for Yandex while using Tool Router? 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. ### 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 Yandex data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)