How to Use the Weblate MCP in Pydantic AI

Q: How do I list all projects with Pydantic AI and Weblate?

You call listprojects to get a master roster. The agent can then drill down into any specific project using getproject for full details.

Q: Can I manage user notifications with Pydantic AI and Weblate?

Yes, you use the listusernotifications tool to see what a user is subscribed to. Management happens via manageusernotifications, allowing controlled updates.

Q: What tools are available for creating new language definitions with Pydantic AI and Weblate?

The agent calls createlanguage when you need a totally new locale. It also provides listlanguages so you can verify the definition before creation.

Q: Can I get detailed information on any user with Pydantic AI and Weblate?

Absolutely. Use getuser to pull a full profile, including details about their group membership and overall statistics using getuserstatistics.

Guaranteed correct localization workflows with Pydantic AI's type safety for Weblate.

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 Pydantic AI

Create your Vinkius account to connect Weblate to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List All Users and Groups

You need to know who's working on what? The agent calls `list_users` to get all account details, or uses `list_groups` for organizational structure. This provides a reliable roster of team members. If you are checking permissions, the tool lets you list roles associated with your user via `list_roles`.

Review Translation Contributions

Track who translated what using `get_user_contributions`. This function returns a history of translations tied directly to a specific user. For performance metrics, the agent retrieves translation counts via `get_user_statistics`. It’s great for reporting: you get clear numbers on contribution volume.

Analyze Project Language Metrics

Need to know how many languages are in a project? The agent uses `list_project_languages` for paginated statistics. For language-specific metrics, call `get_language_statistics`. This helps you see if certain translation pairs need more attention or resources.

Setup guide

Set up Weblate MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "weblate-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Weblate tools.",
)

result = await agent.run("List recent Weblate transactions")
print(result.output)

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 Pydantic AI

You call `list_projects` to get a master roster. The agent can then drill down into any specific project using `get_project` for full details.

Yes, you use the `list_user_notifications` tool to see what a user is subscribed to. Management happens via `manage_user_notifications`, allowing controlled updates.

The agent calls `create_language` when you need a totally new locale. It also provides `list_languages` so you can verify the definition before creation.

Absolutely. Use `get_user` to pull a full profile, including details about their group membership and overall statistics using `get_user_statistics`.

The server deals with user accounts, language definitions, and project components. The most sensitive data type is the `user translation statistics` record.

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