How to Use the Fulcrum MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK connect to Fulcrum?

You'll use the MCPServerStreamableHttp class and pass your Vinkius endpoint URL. The agent auto-discovers all the Fulcrum tools like createrecord and queryrecordssql when it starts up. Set cacheToolsList=True in production so it doesn't have to fetch them every time.

Q: What's the best way to handle large datasets with Fulcrum and the OpenAI Agents SDK?

For large reports, use queryrecordssql. It pushes the heavy lifting to the server instead of pulling thousands of records with listfieldrecords. This keeps your agent's memory usage down and gets you the answer faster.

Q: How do I check if the Fulcrum connection is working from my OpenAI agent?

The simplest way is to have your agent call the checkapistatus tool. It's a lightweight ping that confirms the MCP server can talk to the Fulcrum API. It's a good first step for any diagnostic workflow.

Let your OpenAI Agents SDK manage Fulcrum field data, run SQL queries on records, and sync your team's work automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fulcrum MCP to OpenAI Agents SDK

Create your Vinkius account to connect Fulcrum 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 Fulcrum with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run SQL on Your Field Data

Give your agent direct SQL access to your Fulcrum dataset. It can run complex reports and aggregations using `query_records_sql` without you having to build a separate reporting API. This is for when a simple record list just won't cut it. Your agent gets the raw power to join, filter, and analyze data on the fly. You define the query, the agent executes it, and you get structured results back. It's a direct line from your agent's logic to your ground-truth data.

Automate Record and Form Management

Your agent can create new field entries on its own. Just give it the data, and it calls `create_record` with the right form ID. No more manual data entry from emails or spreadsheets. It can also pull form structures with `get_form_schema` to understand exactly what data is expected. This means you can build workflows that react to external events. An agent can watch an inbox, parse an attachment, and then create a validated Fulcrum record—all without human intervention. Use `list_data_forms` to see which apps are available first.

Manage Teams and Webhooks with an MCP Server

Let your agent handle user and system administration. It can check who is on the team with `list_organization_members` or see their permissions by calling `list_member_roles`. This is perfect for building automated onboarding or auditing bots. Beyond people, your agent can inspect your system's plumbing. It uses `list_webhooks` to see what external integrations are configured, helping you debug data sync issues or verify that your event pipelines are set up correctly.

Setup guide

Set up Fulcrum 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 Fulcrum tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fulcrum 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="Fulcrum Agent",
            instructions="You have access to Fulcrum 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 Fulcrum. 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 Fulcrum 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 Fulcrum MCP in OpenAI Agents SDK

You'll use the `MCPServerStreamableHttp` class and pass your Vinkius endpoint URL. The agent auto-discovers all the Fulcrum tools like `create_record` and `query_records_sql` when it starts up. Set `cacheToolsList=True` in production so it doesn't have to fetch them every time.

The OpenAI Agents SDK doesn't have a built-in filter for tools from a single MCP Server. You control access by creating different Vinkius endpoint tokens with specific permissions. For fine-grained control, you'd implement logic in your agent's code to restrict calls to certain tools.

For large reports, use `query_records_sql`. It pushes the heavy lifting to the server instead of pulling thousands of records with `list_field_records`. This keeps your agent's memory usage down and gets you the answer faster.

The simplest way is to have your agent call the `check_api_status` tool. It's a lightweight ping that confirms the MCP server can talk to the Fulcrum API. It's a good first step for any diagnostic workflow.

Your agent will handle your organization's field data, including form structures, record contents, and user lists. All communication is funneled through your unique Vinkius endpoint token, which secures the connection. The server itself runs in an ephemeral, zero-trust sandbox, so your data is only processed for the duration of the request.

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