How to Use the Hive AI MCP in Pydantic AI

Q: How do I integrate Hive AI tools into Pydantic AI?

You use the MCPToolset class initialized with the Vinkius server URL and pass it to your Pydantic AI Agent's toolsets list. The framework dynamically registers tools like moderatetext and validates their outputs.

Q: Does Pydantic AI validate the output of Hive AI async tasks?

Yes, when your Pydantic AI agent calls getasynctaskresult or getasynctaskstatus, the framework validates the returned JSON structure against strict schemas. This ensures your async moderation pipelines are completely type-safe.

Q: How does Hive AI detect synthetic media in Pydantic AI?

Your Pydantic AI agent invokes detectaigeneratedimage or detectaigeneratedtext to check files. The validation layer ensures the confidence scores are parsed as precise floats before your agent makes a decision.

Q: Can I inspect project configurations using this setup?

Yes, you can call getprojectdetails and listavailablemodels to fetch your workspace settings. The returned metadata is automatically structured and validated by the Pydantic AI framework.

Get type-safe content moderation in Pydantic AI by validating Hive AI outputs against strict runtime schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hive AI MCP to Pydantic AI

Create your Vinkius account to connect Hive AI 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 Hive AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Moderation with Pydantic AI

This MCP Server delivers type-safe validation for `moderate_text` and `moderate_image` within your Pydantic AI workflows. When you connect this server, the tools return structured data that is validated against strict Python type schemas at runtime. This strict validation prevents your Pydantic AI agent from processing corrupt or incomplete moderation payloads. Your agent can confidently call `moderate_text` knowing that the safety flags and score fields match your application's expected types perfectly.

Validate Synthetic Content Detections at Runtime

Enforce strict runtime typing on `detect_ai_generated_image` and `detect_ai_generated_text` using Pydantic AI. This MCP setup ensures your spam detection logic never fails silently because the framework validates the confidence scores before your code acts on them. If a user submits a suspicious document, your Pydantic AI agent calls `detect_ai_generated_text`. Because the framework enforces type correctness, you can safely write business logic that depends on the exact float values of the detection scores.

Type-Checked Async Workflows for Heavy Media

Validate background media processing jobs using `moderate_video_async` and `moderate_audio_async` in Pydantic AI. This MCP server lets your agent spin up background jobs while ensuring the returned task IDs are validated at runtime. The Pydantic AI agent tracks status using `get_async_task_status` and retrieves the final payload with `get_async_task_result`. Every step of this asynchronous loop is backed by strict type validation, making your media pipeline incredibly resilient.

Setup guide

Set up Hive AI 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": {
        "hive-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You use the `MCPToolset` class initialized with the Vinkius server URL and pass it to your Pydantic AI Agent's toolsets list. The framework dynamically registers tools like `moderate_text` and validates their outputs.

Yes, when your Pydantic AI agent calls `get_async_task_result` or `get_async_task_status`, the framework validates the returned JSON structure against strict schemas. This ensures your async moderation pipelines are completely type-safe.

Your Pydantic AI agent invokes `detect_ai_generated_image` or `detect_ai_generated_text` to check files. The validation layer ensures the confidence scores are parsed as precise floats before your agent makes a decision.

Yes, you can call `get_project_details` and `list_available_models` to fetch your workspace settings. The returned metadata is automatically structured and validated by the Pydantic AI framework.

All images, text, audio, and video content moderation data are sent securely via isolated HTTP requests. The Vinkius runtime executes the server in an ephemeral container, ensuring your Pydantic AI moderation payloads are never cached or exposed to unauthorized networks.

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