How to Use the DeepAI MCP in Pydantic AI

Q: How do I add the DeepAI MCP Server to my Pydantic AI project?

Run pip install "pydantic-ai-slimmcp" to get the required dependencies. Then initialize an MCPToolset with your HTTP endpoint and add it to your agent.

Build type-safe image generation pipelines by connecting DeepAI to your Pydantic AI applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepAI MCP to Pydantic AI

Create your Vinkius account to connect DeepAI 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 DeepAI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe DeepAI Image Generation

This MCP server provides five core visual tools, including `generate_image` and `edit_image`. The agent takes your text instructions and executes the corresponding visual modifications. Pydantic AI validates every single response from these endpoints at runtime. If the API returns a malformed URL or unexpected JSON structure, the framework fails loudly rather than silently passing corrupted data into your application.

Strict Validation for Background Removal

Isolating subjects from their backgrounds requires the `remove_background` tool. The agent sends the original photo and waits for the processed transparent asset. You define the exact expected output schema in your Python code. If the resulting asset does not match your strict Pydantic models, the execution stops immediately, ensuring your downstream systems only receive valid files.

Upscale Images via MCP Server Toolsets

Restoring visual fidelity relies on the `super_resolution` and `colorize_image` endpoints. These functions take low-quality or monochromatic inputs and return modernized, high-quality versions. Integration uses the unified MCPToolset approach rather than deprecated HTTP methods. You pass the toolset directly to your Agent constructor, giving any model instant access to the restoration capabilities.

Setup guide

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

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

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

Run pip install "pydantic-ai-slim[mcp]" to get the required dependencies. Then initialize an MCPToolset with your HTTP endpoint and add it to your agent.

Yes, the framework validates all incoming data against your defined models. Any mismatch triggers an immediate runtime error.

The framework is entirely model-agnostic. You can route the image generation tools through local LLMs just as easily as hosted APIs.

The setup relies on Streamable HTTP transport. You configure this through the unified toolset class.

The system processes raw image data and generation prompts. Vinkius wraps this entire operation in an ephemeral sandbox, ensuring your visual assets are never stored on disk after the HTTP request concludes.

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