How to Use the Jestor MCP in OpenAI Agents SDK

Q: How do I initialize the Jestor MCP Server in the OpenAI Agents SDK?

Install the package using pip install openai-agents first. Then, initialize MCPServerStreamableHttp using MCPServerStreamableHttpParams with your Vinkius endpoint. Wrap it in an async context manager and pass it via the mcpservers list to your Agent.

Run production-grade OpenAI agents with direct, validated access to your Jestor tables and workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jestor MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate database queries before execution

OpenAI Agents SDK uses built-in guardrails to check actions before your agent touches the database. When your agent calls `get_record` or `list_records`, the SDK validates the parameters against your actual schema before firing the request. This keeps your production data clean and prevents weird, half-formed queries from hitting your live tables. You also get full tracing inside the OpenAI dashboard to see exactly when and why an agent decided to look up a record. If an agent tries to modify something it shouldn't, the execution halts immediately. It is a bulletproof way to let LLMs interact with your operational data without giving them raw database access.

Manage multi-agent handoffs for complex tasks

You do not want a single agent trying to handle user permissions, schema lookups, and data entry all at once. Instead, spin up specialized agents and hand off control between them. One agent can use `list_users` to find the right owner, then hand the task to a database agent to run `get_object` and map out the fields. This MCP Server exposes 10 distinct tools, making it easy to split responsibilities. Your routing agent handles the high-level logic, while dedicated worker agents focus strictly on fetching schemas or auditing workflows. It keeps your code modular and your token costs down.

Auto-discover Jestor tools with zero configuration

Setting up this MCP Server with the OpenAI Agents SDK takes about five lines of Python. Just pass the server URL into `MCPServerStreamableHttp` within an async context manager and hand it to your Agent constructor. The SDK automatically maps every endpoint—from `list_webhooks` to `list_dashboards`—directly into the agent's available toolset. To keep performance snappy in production, make sure to set `cacheToolsList=True` in your configuration. This prevents the SDK from rebuilding the tool schema on every single turn, giving you near-instant tool discovery. Your agent immediately knows how to query your data without manual JSON schema writing.

Setup guide

Set up Jestor 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 Jestor tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` first. Then, initialize `MCPServerStreamableHttp` using `MCPServerStreamableHttpParams` with your Vinkius endpoint. Wrap it in an async context manager and pass it via the `mcp_servers` list to your Agent.

Yes, you can control tool access by setting explicit permissions on the Vinkius token or by filtering tools at the SDK level. If you only want the agent reading data, you can expose `list_records` and `get_record` while hiding schema alteration tools.

The SDK queries the MCP Server endpoint during startup to inspect all available tools. It reads the schemas for tools like `list_workflows` and `list_webhooks` automatically, converting them into OpenAI-compatible tool definitions.

Open your OpenAI developer dashboard and locate the run trace for your agent. You will see the exact payloads passed to tools like `get_object` along with the raw JSON responses returned by the server.

Vinkius hosts the server in an ephemeral, zero-trust sandbox where your API keys are never exposed to the LLM. When the agent calls `get_me` to verify connection status, the authentication header is injected securely at the proxy layer, keeping your credential logs clean and inaccessible to the model.

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