How to Use the Metatext MCP in Pydantic AI

Q: How is my NLP inference payload data secured?

All text payloads sent to runmodelinference are processed in memory within our isolated, zero-trust V8 sandbox. We never write your inference inputs, outputs, or dataset records to persistent storage.

Run type-safe NLP inference and dataset operations using Metatext with Pydantic AI validation through our 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 Metatext MCP to Pydantic AI

Create your Vinkius account to connect Metatext 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 Metatext with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute type-safe inference with this MCP Server

This server registers the `run_model_inference` tool to let your Pydantic AI agents run predictions with strict runtime type-checking. Every prediction output is validated against your Pydantic schemas immediately upon receipt. If the underlying NLP model returns unexpected fields, the framework raises a validation error instead of passing bad data down the line. This ensures your downstream logic never breaks due to silent payload changes.

Validate dataset records at the schema level

The integration uses `create_dataset_record` and `get_dataset_details` to build type-safe data pipelines. Before a record is written, Pydantic AI validates the structure to ensure it matches your target dataset's requirements. You can also use `list_dataset_records` to inspect existing data. The framework parses the returned records into structured Python objects, giving your agent clean, typed data to work with.

Type-safe model discovery and metadata auditing

The server exposes `list_nlp_models` and `search_nlp_models` to let your agent find models without risking runtime crashes. The search results are parsed into typed models so your agent can safely inspect the training state. By calling `get_model_details` and `list_model_deployments`, your agent can verify which endpoints are active. Because everything is typed, you can write clean code that handles deployment states without defensive try-except blocks.

Setup guide

Set up Metatext 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": {
        "metatext-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Metatext 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 Metatext. 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 Metatext 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 Metatext MCP in Pydantic AI

Install the slim package with MCP support, then initialize the unified toolset with your server's HTTP endpoint. Pass the toolset directly to your agent to make all ten NLP tools available.

The framework will catch the discrepancy immediately and raise a validation error. This prevents corrupted data from tools like `get_dataset_details` from poisoning your agent's state or decision loop.

Yes, because the framework is model-agnostic, you can use local models to drive the agent while it calls `run_model_inference` on your remote NLP models.

No, you should use the new unified toolset class instead of the deprecated HTTP client. This ensures compatibility with the latest MCP updates and streamable transports.

All text payloads sent to `run_model_inference` are processed in memory within our isolated, zero-trust V8 sandbox. We never write your inference inputs, outputs, or dataset records to persistent storage.

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