How to Use the Grain MCP in Pydantic AI

Q: How do I set up the Grain MCP server with Pydantic AI?

You initialize the MCPToolset with your Vinkius HTTP URL. This registers all 12 MCP tools, including listrecordings and getinsights, directly into your Pydantic AI agent instance.

Q: Can I use Pydantic AI to validate summaries from Grain?

Yes. You can call getinsights to retrieve the meeting summary and pass it through a Pydantic model to ensure it contains required fields like project status and key decisions.

Q: Does this integration support uploading videos?

Yes, you can use uploadvideo to send external files to Grain. Your agent can track the upload process and validate the metadata of the resulting recording using standard Pydantic models.

Build type-safe meeting intelligence pipelines using Pydantic AI and Grain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grain MCP to Pydantic AI

Create your Vinkius account to connect Grain 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 Grain with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe transcript parsing with Pydantic AI

If you need guaranteed data structures from your meeting notes, this integration is the answer. When your Pydantic AI agent calls `get_transcript`, the returned data is validated against strict Python schemas at runtime. This prevents silent failures in your data pipeline. If a speaker name is missing or a timestamp format changes, the system catches it immediately, ensuring your database imports never break.

Strict extraction of action items

Stop guessing what format your agent will return. Use `get_action_items` inside your Pydantic AI agent to force the model's output into a rigid schema, complete with assignees and deadlines. If the model tries to hallucinate a field or returns unstructured text, the runtime validation fails loudly. This guarantees that your task-tracking systems only receive clean, actionable data.

Search and tag recordings reliably

Manage your entire meeting catalog without worrying about API drift. Your agent can execute `search_recordings` and `list_tags` to categorize your library based on actual meeting content. By wrapping these MCP server tools in Pydantic models, you ensure that every search result matches the exact dataclass your frontend expects. It makes building custom search interfaces fast and predictable.

Setup guide

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

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

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

You initialize the `MCPToolset` with your Vinkius HTTP URL. This registers all 12 MCP tools, including `list_recordings` and `get_insights`, directly into your Pydantic AI agent instance.

The framework will raise a validation error at runtime. This ensures that tools like `get_recording` conform strictly to your defined Python types before your agent can use the underlying MCP server.

Yes. You can call `get_insights` to retrieve the meeting summary and pass it through a Pydantic model to ensure it contains required fields like project status and key decisions.

Yes, you can use `upload_video` to send external files to Grain. Your agent can track the upload process and validate the metadata of the resulting recording using standard Pydantic models.

All meeting data, transcripts, and workspace lists are accessed via an encrypted zero-trust connection. V8 isolation ensures no customer data is ever written to disk or exposed.

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