How to Use the Localazy (AI Translation & Localization API) MCP in Pydantic AI

Q: How do I add Localazy (AI Translation & Localization API) to a Pydantic AI agent?

Install pydantic-ai-slimmcp and initialize the MCP Server using MCPToolset with the Vinkius HTTP URL. Pass this toolset into the Agent constructor to expose the localization tools.

Q: Is the older MCPServerHTTP class still used for Localazy (AI Translation & Localization API) in Pydantic AI?

No, MCPServerHTTP is deprecated. Use the unified MCPToolset approach to connect to the external server securely.

Q: Can Pydantic AI validate the output of Localazy (AI Translation & Localization API) tools?

Yes, every response from the MCP Server tools like listfiles is validated against strict Pydantic models. Any unexpected schema changes will trigger an immediate runtime error.

Q: How can my agent modify a single source key?

The agent calls updatesourcekey with the target key ID and the new metadata. This allows precise updates to individual strings without touching the rest of the file.

Build crash-safe localization pipelines by validating translation data at runtime with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Localazy (AI Translation & Localization API) MCP to Pydantic AI

Create your Vinkius account to connect Localazy (AI Translation & Localization API) 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 Localazy (AI Translation & Localization API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate import formats dynamically

`list_import_formats` queries the platform to find all supported file types and their configuration parameters. Pydantic AI parses this payload into typed schemas to prevent invalid file uploads. If the server returns unrecognized formats, the framework raises a validation error immediately. This protects your automated translation pipelines from processing corrupt data.

Type-safe glossary management with this MCP Server

`list_glossary_terms` pulls the current glossary list directly into your agent's context. The framework validates every glossary object against strict Python types before your agent acts on them. Your agent updates terms safely using `update_glossary_term` or removes them with `delete_glossary_term`. Strict schemas ensure you never pass malformed payloads to the API.

Verify published CDN assets

`list_cdn_metadata` fetches the metadata URLs for your published release tags on the CDN. This lets your agent check if the latest translations are live. The returned URLs are validated as strict URI types by the framework. This ensures your application never attempts to load assets from malformed CDN endpoints.

Setup guide

Set up Localazy (AI Translation & Localization API) 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": {
        "localazy-ai-translation-localization-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Localazy (AI Translation & Localization API) tools.",
)

result = await agent.run("List recent Localazy (AI Translation & Localization API) 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 Localazy. 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 Localazy (AI Translation & Localization API) 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 Localazy (AI Translation & Localization API) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize the MCP Server using `MCPToolset` with the Vinkius HTTP URL. Pass this toolset into the `Agent` constructor to expose the localization tools.

No, `MCPServerHTTP` is deprecated. Use the unified `MCPToolset` approach to connect to the external server securely.

Yes, every response from the MCP Server tools like `list_files` is validated against strict Pydantic models. Any unexpected schema changes will trigger an immediate runtime error.

The agent calls `update_source_key` with the target key ID and the new metadata. This allows precise updates to individual strings without touching the rest of the file.

The MCP Server runs in an isolated V8 sandbox on Vinkius, meaning your localization keys and project configurations are never cached or logged. Your API tokens are injected securely at runtime and never exposed to the LLM.

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