How to Use the Crowdin MCP in AutoGen

Q: How do I register Crowdin MCP tools with an AutoGen agent?

Install autogen-extmcp and use mcpservertools with the Vinkius server URL. Pass the generated tools list directly to your AutoGen AssistantAgent constructor.

Q: Can AutoGen agents coordinate Crowdin translation workflows?

Yes, your agents use listprojecttasks and listprojectfiles to monitor progress. They debate task status and file completion to coordinate handoffs between translation and proofreading stages.

Q: How do AutoGen agents use Crowdin translation memories?

Your agents call listtranslationmemories to check available translation resources. They discuss whether existing segments are sufficient for a new project or if they need to request new translations.

Build AutoGen multi-agent debates to resolve Crowdin tasks using this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crowdin MCP to AutoGen

Create your Vinkius account to connect Crowdin to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Crowdin with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Crowdin task assignments in AutoGen

The `list_project_tasks` tool allows your AutoGen agents to coordinate translation and proofreading assignments. A project manager agent retrieves the active tasks, while a QA agent reviews the assigned linguist credentials to ensure quality standards. These agents debate whether to reassign tasks based on historical performance metrics. By using this MCP server, your AutoGen group chat automatically resolves resource bottlenecks before they stall your release schedule.

Review Crowdin screenshots using AutoGen agents

The `list_project_screenshots` tool provides visual context tags and linked string identifiers to your AutoGen conversation thread. One agent flags missing visual context, while another matches screenshot IDs against active string keys. The agents negotiate which visual assets need updates to guide translators. They use `get_file_details` to verify if the corresponding source files are ready for visual validation.

Audit Crowdin translation files with AutoGen

The `list_project_files` tool feeds file paths and progress metrics directly into your AutoGen multi-agent workspace. A developer agent and a localization agent argue over which files require immediate translation updates based on completion percentages. This cooperative workflow uses `get_project_details` to check target languages before finalizing the file list. The agents reach consensus on release readiness without requiring manual project audits.

Setup guide

Set up Crowdin MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Crowdin tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Crowdin_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Crowdin data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Crowdin_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Crowdin data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Crowdin. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Crowdin now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Crowdin MCP in AutoGen

Install autogen-ext[mcp] and use mcp_server_tools with the Vinkius server URL. Pass the generated tools list directly to your AutoGen AssistantAgent constructor.

Yes, your agents use `list_project_tasks` and `list_project_files` to monitor progress. They debate task status and file completion to coordinate handoffs between translation and proofreading stages.

Your agents call `list_translation_memories` to check available translation resources. They discuss whether existing segments are sufficient for a new project or if they need to request new translations.

Yes, you can connect the server using StreamableHttpServerParams. This allows your agents to call tools like `list_supported_languages` with low latency during live group chats.

Vinkius manages your authentication token securely, keeping it hidden from the AutoGen agents. Your translation metadata, retrieved via `list_projects`, is processed in a secure sandbox and never stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript