How to Use the Fibery MCP in Pydantic AI

Q: How do I connect the Fibery MCP Server to a Pydantic AI agent?

Instantiate the MCPToolset with your Vinkius streamable HTTP URL and pass it to the Pydantic AI Agent constructor. This unified approach exposes all 11 Fibery tools to your type-safe agent.

Drive type-safe Fibery workspace updates using Pydantic AI to validate every entity and comment before it hits production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fibery MCP to Pydantic AI

Create your Vinkius account to connect Fibery 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 Fibery with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Pydantic AI Validation for your Fibery MCP Server

If the Fibery API returns unexpected fields, your Pydantic AI agent won't guess what to do. Pydantic AI forces every response from Fibery's `get_entity` or `query_entities` through strict Python type checks at runtime. If the Fibery schema changes, the Pydantic AI toolset fails loudly with a validation error instead of passing corrupt data to your LLM. This guarantees that your Pydantic AI agent only works with clean, structured Fibery data.

Type-Safe Fibery Entity Operations via Pydantic AI

Writing data back to your Fibery workspace using Pydantic AI requires strict type precision. This server lets you wrap Fibery's `create_entity` and `update_entity` in Pydantic AI models so your agent cannot send bad field types. The Pydantic AI agent validates the arguments against your models before calling the Fibery API. This prevents runtime errors and keeps your Fibery databases free of garbage data when using Pydantic AI.

Model-Agnostic Fibery Automation with Pydantic AI

You are not locked into a single model provider when using this Fibery MCP Server with Pydantic AI. You can run your Fibery workspace automation with Pydantic AI using OpenAI, Anthropic, Gemini, or even a local Llama model. Your Pydantic AI agent can search for items with `search_entities` and manage conversations with `add_comment` in Fibery using whichever model fits your budget. The underlying Fibery tool schemas remain perfectly consistent across all Pydantic AI configurations.

Setup guide

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

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

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

Instantiate the `MCPToolset` with your Vinkius streamable HTTP URL and pass it to the Pydantic AI `Agent` constructor. This unified approach exposes all 11 Fibery tools to your type-safe agent.

The Pydantic AI framework will raise a validation error immediately if the Fibery API returns a field that is not in your model. This prevents your Pydantic AI agent from processing unexpected Fibery data shapes.

Yes, you can define strict schemas for data returned by Fibery's `get_comments` and `get_entity` tools. The Pydantic AI framework validates the Fibery API payloads against these models before your agent can use them.

No, the Pydantic AI framework is model-agnostic. You can use this server to manage your Fibery workspace databases with GPT-4o, Claude 3.5 Sonnet, or any local model supported by the library.

Your Fibery API tokens and workspace schemas are processed entirely in memory within an isolated V8 sandbox hosted on our MCP Server. We never store your Fibery entity details, user lists, or comment text, ensuring strict compliance with Pydantic AI enterprise data policies.

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