How do I find my Fibery Workspace name?

Your workspace name is the subdomain in your Fibery URL. For example, if you access Fibery at `https://my-team.fibery.io`, your workspace name is `my-team`.

How do I generate a Fibery API Token?

In your Fibery workspace, go to **Settings > API**, click on **Create New Token**, give it a name, and copy the generated token immediately.

Can I query custom fields created in my spaces?

Yes! Use the `get_schema` tool to see the fully qualified names of your custom fields, and then include them in the `select_json` parameter of the `query_entities` tool.

Fibery MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Fibery
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Fibery through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Fibery "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Fibery?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Fibery MCP Server

Fibery is a work management platform that adapts to your unique processes. This MCP server allows your AI agent to interact with your Fibery workspace seamlessly.

Pydantic AI validates every Fibery tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Space & Schema Discovery — List all your spaces (apps) and retrieve the full schema to understand your custom databases and fields.
Entity Management — Query, create, update, and delete entities across any of your custom databases flawlessly.
Comment Integration — Read and add comments to entities to keep your team in sync natively.
Advanced Querying — Use granular filters and field selections to retrieve exactly the data you need synchronously.
Cross-Database Search — Search for information across your entire workspace flawlessly through the agent.

The Fibery MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Fibery to Pydantic AI via MCP

Follow these steps to integrate the Fibery MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from Fibery with type-safe schemas

Why Use Pydantic AI with the Fibery MCP Server

Pydantic AI provides unique advantages when paired with Fibery through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Fibery integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Fibery connection logic from agent behavior for testable, maintainable code

Fibery + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Fibery MCP Server delivers measurable value.

Type-safe data pipelines: query Fibery with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Fibery tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Fibery and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Fibery responses and write comprehensive agent tests

Fibery MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Fibery to Pydantic AI via MCP:

add_comment

Add a comment to an entity

create_entity

Create a new entity in a specific database

delete_entity

Delete an entity

get_comments

Retrieve comments for a specific entity

get_entity

Get a specific entity by its UUID

get_schema

Retrieve the full schema of the workspace, including all databases (types) and fields

list_apps

List all Fibery apps (spaces)

list_users

List all users in the Fibery workspace

query_entities

Query entities from a specific database (type)

search_entities

Search for entities by keyword across all databases

update_entity

Update an existing entity

Example Prompts for Fibery in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Fibery immediately.

"List all active spaces in my Fibery account."

"Show me the tasks assigned to me in the 'Software Development' space."

"Add a comment to task UUID-123 saying 'The client approved the design'."

Troubleshooting Fibery MCP Server with Pydantic AI

Common issues when connecting Fibery to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Fibery + Pydantic AI FAQ

Common questions about integrating Fibery MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Fibery MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.