How to Use the Weblate MCP in AutoGen

Q: How do I list all projects for review using Weblate and AutoGen?

The listprojects tool provides the full roster of localization projects. An agent can then take this list and feed it into a multi-agent debate to prioritize which project needs attention first.

Q: Can I get language statistics for a whole project using Weblate and AutoGen?

Yes, use listprojectlanguages. This gives paginated stats on every language in one specific project. It's ideal for having multiple agents debate whether the effort should be focused on adding new languages or fixing existing ones.

Q: What is the process for creating a user account using Weblate and AutoGen?

An agent first calls createuser to make the account. Then, another agent might use getgroup to ensure that the new user is automatically assigned to the correct team group.

Q: What tools are available for managing project labels using Weblate and AutoGen?

Agents manage these labels with dedicated calls like listprojectlabels. They use this information when creating or modifying projects, ensuring consistency across the entire product.

Run consensus-driven localization workflows with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weblate MCP to AutoGen

Create your Vinkius account to connect Weblate 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 Weblate with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit team permissions across Weblate.

Need to check who can do what? The `get_role` tool provides detailed permission codenames for any role. You should also call `list_roles` to get a complete list of roles assigned to an account. If you need to manage team structure, use `get_group`. This shows the group's current mix of roles, projects, and components, allowing agents to debate who needs more access.

Perform structured project setup.

When starting a new feature, an agent can first run `create_project` to initialize it. Then, another agent uses `create_project_component` to define the required parts of the UI. The whole process is documented by calling `list_projects` beforehand. Agents can also use `get_project_repository` to check if the project's version control status requires a push or pull before proceeding with localization.

Monitor user activity and accounts.

To track contributions, agents use `get_user_contributions`, listing specific translations tied to an account. They can also call `list_users` to get a full roster of available users. If an agent needs to change details, it uses `update_user`. This controlled process ensures that user data modifications are deliberate and vetted by multiple agents.

Setup guide

Set up Weblate 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 Weblate 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="Weblate_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Weblate 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="Weblate_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Weblate 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 Weblate. 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 Weblate 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 Weblate MCP in AutoGen

The `list_projects` tool provides the full roster of localization projects. An agent can then take this list and feed it into a multi-agent debate to prioritize which project needs attention first.

Yes, use `list_project_languages`. This gives paginated stats on every language in one specific project. It's ideal for having multiple agents debate whether the effort should be focused on adding new languages or fixing existing ones.

An agent first calls `create_user` to make the account. Then, another agent might use `get_group` to ensure that the new user is automatically assigned to the correct team group.

Agents manage these labels with dedicated calls like `list_project_labels`. They use this information when creating or modifying projects, ensuring consistency across the entire product.

This server handles core administrative and identity data. It processes specific user metadata like usernames, email addresses, group memberships, roles, and contribution records.

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