How to Use the Fellow MCP in Pydantic AI

Q: Can my agent safely archive old tasks?

Yes, the agent calls archiveactionitem to hide tasks from active views. Because the operation is validated at runtime, you avoid sending incorrect IDs to the API.

Run type-safe meeting workflows with Pydantic AI, validating every action item, note, and transcript at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to Pydantic AI

Create your Vinkius account to connect Fellow 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 Fellow with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Action Item Tracking

The `list_action_items` tool returns structured task data that your Pydantic AI agent validates against strict Python schemas. This prevents your pipeline from processing corrupted task payloads or hallucinated dates. When an agent calls `complete_action_item` or `archive_action_item`, the inputs are verified before hitting the API. You can also use `get_action_item` to fetch a single task with guaranteed type safety, eliminating runtime surprises.

Validated Note and Agenda Parsing

The `get_note` tool retrieves complete meeting notes, including agendas and decisions, directly into your validated agent state. Your agent uses `list_notes` to locate the correct document ID before fetching the content. If you need to clean up your workspace, the agent uses `delete_note` to remove old records. Because Pydantic AI enforces type boundaries, you can be sure the target ID matches the exact format required by the API. This MCP Server integration makes document management predictable.

Secure Audio and Transcript Management with Pydantic AI

The `get_transcript` tool extracts raw text from your meeting audio files. Your agent first calls `list_recordings` to find the session, then uses `get_recording` to inspect the metadata. To keep your storage optimized, the agent can call `delete_recording` on old files. By using this MCP toolset, you ensure that every transcript and recording object conforms to your application's data models.

Setup guide

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

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

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

Import the MCP toolset package and initialize it with your Vinkius HTTP endpoint. Pass the toolset object to your agent constructor to enable type-safe meeting tools.

The framework will raise a validation error immediately. This prevents your agent from making decisions based on malformed meeting notes or corrupt action items.

Vinkius handles the authorization layer using a single endpoint token. Your agent verifies the connection by calling `get_current_user` to fetch the authorized profile.

Yes, the agent calls `archive_action_item` to hide tasks from active views. Because the operation is validated at runtime, you avoid sending incorrect IDs to the API.

Yes, all validation occurs locally within your Python runtime. Your meeting notes, transcripts, and action items are fetched directly from the secure Vinkius endpoint without third-party exposure.

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