How to integrate Crowdin MCP with Pydantic AI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Crowdin Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Crowdin to Pydantic AI using the Composio tool router. By the end, you'll have a working Crowdin agent that can create a new crowdin project for our app, add new source file to the translations project, assign sprint label to specific string ids, delete obsolete translation branch from project through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Crowdin account through Composio's Crowdin 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 your Composio API key and User ID
  • How to create a Composio Tool Router session for Crowdin
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Crowdin workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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

The Crowdin MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Crowdin account. It provides structured and secure access to your localization projects, so your agent can manage branches, organize files, label content, automate webhooks, and orchestrate translation workflows on your behalf.

  • Branch and project management: Easily have your agent create, delete, or organize Crowdin projects and branches to streamline new releases or features.
  • Dynamic file handling: Let your agent add new files to projects, ensuring your translation assets are always up to date and properly organized by branch or directory.
  • Labeling and content categorization: Direct your agent to create, assign, or remove labels on resources and strings, helping you segment and track translation tasks with precision.
  • Workflow automation with webhooks: Automate your translation process by having the agent set up or remove webhooks for real-time notifications and integrations.
  • Resource cleanup and maintenance: Empower your agent to delete obsolete branches, labels, webhooks, or entire projects, keeping your Crowdin workspace clean and focused.

Supported Tools & Triggers

Tools
Add BranchTool to create a new branch in a crowdin project.
Add FileTool to add a new file to a crowdin project.
Add LabelTool to create a new label in a crowdin project.
Create Crowdin ProjectTool to create a new project in crowdin.
Add WebhookTool to create a new webhook in a crowdin project.
Assign Label to StringsTool to assign the specified label to provided string ids in a project.
Delete BranchTool to delete a specific branch from a crowdin project.
Delete LabelTool to delete the label identified by the specified label id in a project.
Delete ProjectTool to delete a crowdin project by its id.
Delete WebhookTool to delete the webhook identified by the specified webhook id in a crowdin project.
Edit FileTool to update file details in a project.
Edit LabelTool to edit a label in a crowdin project.
Edit ProjectTool to update project details using json-patch.
Edit StringTool to update string details in a crowdin project.
Get LabelTool to retrieve information about the label identified by the specified label id in a project.
Get LanguageTool to retrieve details of a specific language.
Get Member InfoTool to retrieve information about a project member.
Get ProjectTool to retrieve details of a specific crowdin project.
Get StringTool to retrieve details of a specific string in a crowdin project.
Get WebhookTool to retrieve information about the webhook identified by the specified webhook id in a project.
List BranchesTool to list all branches in a crowdin project.
List FilesTool to list files in a crowdin project.
List LabelsTool to list labels in a crowdin project.
List LanguagesTool to retrieve a list of supported languages.
List Project MembersTool to list members in a crowdin project.
List ProjectsTool to retrieve a list of all crowdin projects with optional filters.
List ReportsTool to list reports for a given crowdin project.
Upload StorageTool to upload a file to crowdin storage.

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 starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming

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 dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Crowdin
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Crowdin
  • MCPServerStreamableHTTP connects to the Crowdin MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Crowdin
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["crowdin"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Crowdin tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
crowdin_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[crowdin_mcp],
    instructions=(
        "You are a Crowdin assistant. Use Crowdin tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Crowdin endpoint
  • The agent uses GPT-5 to interpret user commands and perform Crowdin operations
  • The instructions field defines the agent's role and behavior

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Crowdin.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Crowdin API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Crowdin and Pydantic AI:

import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Crowdin
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["crowdin"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    crowdin_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[crowdin_mcp],
        instructions=(
            "You are a Crowdin assistant. Use Crowdin tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Crowdin.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Crowdin through Composio's Tool Router. With this setup, your agent can perform real Crowdin actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Crowdin for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Crowdin MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Crowdin MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Crowdin MCP with Claude Agent SDK

Google ADK

Google ADK

Use Crowdin MCP with Google ADK

LangChain

LangChain

Use Crowdin MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Crowdin MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Crowdin MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Crowdin MCP with LlamaIndex

CrewAI

CrewAI

Use Crowdin MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Pydantic AI?

Yes, you can. Pydantic 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 Crowdin tools.

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

Yes, absolutely. You can configure which Crowdin 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 Crowdin 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.

Book a call↗Get started for free