How to Use the Tubular MCP in Pydantic AI

Q: How do I check audience overlap using Tubular and Pydantic AI?

You call getaudienceoverlap. The strength here is that because of the validation layer, you know exactly what structure the resulting data will have. You get reliable answers every time.

Q: Can I check video metrics reliably using Tubular and Pydantic AI?

Yes. Use getvideoinsights to gather all performance metrics for a single video. The Pydantic layer guarantees the output fields you expect are present and correctly typed.

Q: How do I find trending videos using Tubular and Pydantic AI?

Run getvideotrends to get a list of popular content. Since this is an MCP Server, the response is validated against expected schemas, so you never have to worry about malformed trend data.

Q: What kind of audience data does this Tubular MCP Server touch?

The server touches audience demographics when calling getvideodemographics. This includes viewing profiles like age, gender, and geographic location for the specific video in question.

Build reliable social analytics agents with Pydantic AI. Guarantee correct audience insights from Tubular without validation errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tubular MCP to Pydantic AI

Create your Vinkius account to connect Tubular 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 Tubular with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Audience Data With MCP Server

Need to know if your target market overlaps with a sponsor's base? Use `get_audience_overlap`. Since this is running through Pydantic AI, you get guaranteed type-safe output every single time. No messy JSON surprises. You can validate the results of `list_sponsors` against audience data to make sure your partnership proposals are solid and structured.

Search & Verify Creator Details

Want to check a competitor? Start with `search_creators`. The agent finds potential creators, but the Pydantic validation ensures that the creator data—like their handle or niche keywords—is always correctly formatted. After you find them, use `get_creator_summary` to pull key metrics. You'll know these stats are reliable because of the runtime schema checking.

Audit Sponsorships Via Pydantic AI

Running a campaign requires tracking every dollar and partner. Use `list_sponsored_campaigns` to pull all current campaigns into one clean list. The validation layer ensures that each record contains the required sponsor ID and start date. Then, you can use `get_video_demographics` to analyze who watched the content associated with those specific campaigns.

Setup guide

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

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

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

You call `get_audience_overlap`. The strength here is that because of the validation layer, you know exactly what structure the resulting data will have. You get reliable answers every time.

Yes. Use `get_video_insights` to gather all performance metrics for a single video. The Pydantic layer guarantees the output fields you expect are present and correctly typed.

Run `get_video_trends` to get a list of popular content. Since this is an MCP Server, the response is validated against expected schemas, so you never have to worry about malformed trend data.

It's built for correctness. The Pydantic layer makes sure that if the API returns unexpected data from any tool, your agent fails loud and clear—no silent corruption.

The server touches **audience demographics** when calling `get_video_demographics`. This includes viewing profiles like age, gender, and geographic location for the specific video in question.

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