How to Use the Fibery MCP in OpenAI Agents SDK

Q: How do I register the Fibery MCP Server with my OpenAI Agents SDK?

Install the OpenAI Agents SDK using pip and configure the MCPServerStreamableHttp client with your Vinkius endpoint. You then pass this server instance to the Agent constructor to auto-discover all 11 Fibery tools.

Q: How does the OpenAI Agents SDK handle schema changes in Fibery?

The OpenAI Agents SDK agent uses getschema to pull the latest Fibery databases and fields at runtime. If you change your Fibery workspace structure, the OpenAI agent adapts immediately without needing a code redeployment.

Q: Will my OpenAI Agents SDK run slower if I use this Fibery MCP Server?

No, because you can set cacheToolsList=True in your OpenAI Agents SDK configuration to avoid redundant Fibery tool discovery calls. You should use searchentities instead of pulling the entire Fibery database to keep your OpenAI agent latency low.

Let your OpenAI Agents SDK coordinate Fibery database updates and assign tasks safely using built-in agent guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Fibery to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK Guardrails for Fibery

Deployed OpenAI Agents SDK processes can cause havoc if they edit the wrong Fibery workspace database. This MCP Server lets you register `get_schema` and `query_entities` with your OpenAI Agents SDK so your agent checks your exact Fibery setup before making changes. The OpenAI Agents SDK built-in validation layer intercepts every call to Fibery's `update_entity` endpoint. If your agent tries to write a bad field type to your Fibery database, the OpenAI Agents SDK blocks the execution and logs the error on your OpenAI dashboard.

Safe Multi-Agent Project Handoffs

You can build a multi-agent Python system where one OpenAI Agents SDK instance finds Fibery issues and another updates them. Your triage agent uses `search_entities` to locate a bug in Fibery, then hands the context off to an OpenAI Agents SDK developer agent. That OpenAI Agents SDK developer agent then invokes `create_entity` or adds a status update using `add_comment` in Fibery. This keeps your OpenAI Agents SDK execution loop clean because each agent only handles the specific Fibery tools it needs.

Traceable Workspace Modifications

Debugging OpenAI Agents SDK actions in production is painful when you do not know why a Fibery entity changed. Running this server with the OpenAI Agents SDK gives you complete tracing for every Fibery `delete_entity` or `update_entity` call. You can open your OpenAI dashboard and see the exact parameters passed by the SDK to `get_entity` or `list_apps` in Fibery. This visibility makes it easy to debug why a specific Fibery database record was updated by your OpenAI Agents SDK.

Setup guide

Set up Fibery MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Fibery tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Fibery tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fibery tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Fibery Agent",
            instructions="You have access to Fibery tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the OpenAI Agents SDK using pip and configure the `MCPServerStreamableHttp` client with your Vinkius endpoint. You then pass this server instance to the `Agent` constructor to auto-discover all 11 Fibery tools.

Yes, you can control tool access by defining specific system instructions or restricting the OpenAI Agents SDK tool list during initialization. This prevents a specialized agent from calling Fibery's `delete_entity` when it only needs to run `get_comments`.

The OpenAI Agents SDK agent uses `get_schema` to pull the latest Fibery databases and fields at runtime. If you change your Fibery workspace structure, the OpenAI agent adapts immediately without needing a code redeployment.

No, because you can set `cacheToolsList=True` in your OpenAI Agents SDK configuration to avoid redundant Fibery tool discovery calls. You should use `search_entities` instead of pulling the entire Fibery database to keep your OpenAI agent latency low.

All Fibery data passing through this MCP Server runs inside an ephemeral, zero-trust V8 sandbox before hitting the OpenAI Agents SDK. Your Fibery API tokens, workspace schemas, and comment threads are never stored or used to train OpenAI models.

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