How to Use the JigsawStack MCP in OpenAI Agents SDK

Q: How do I set up the JigsawStack MCP Server with OpenAI Agents SDK?

Install openai-agents via pip first. Then initialize MCPServerStreamableHttp using the Vinkius endpoint URL. The SDK auto-discovers all seven tools from the MCP Server.

Q: Does the JigsawStack integration support OpenAI Agents SDK caching?

Yes, it does. Set cacheToolsList=True in your configuration to avoid fetching the tool definitions on every single agent run, which shaves off latency.

Q: Can I use JigsawStack with OpenAI Agents SDK agent handoffs?

Yes, absolutely. You can have a routing agent use checkprofanitytext to inspect inputs, then hand off clean data to a translation agent that uses translatetext.

Q: How does the OCR tool handle bad image URLs?

If extracttextfromimage gets a broken URL, it returns a clear error string. Your agent catches this failure in the tracing dashboard and can try an alternative URL.

Q: How does JigsawStack keep my image and text data private?

All images sent to checknsfwimage and text sent to summarizetext are processed in ephemeral memory. Vinkius runs the MCP Server in a zero-trust sandbox, meaning your raw files and strings are never stored or used for model training.

Equip your OpenAI Agents SDK with production-ready web scraping, OCR, and content moderation tools using this zero-config MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JigsawStack MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Moderate media with OpenAI Agents SDK

The `check_nsfw_image` tool inspects image URLs for explicit content before your agent passes them to other pipeline steps. This means you can block unsafe uploads at the API boundary, keeping your downstream OpenAI Agents SDK runs clean without manual guardrail code. You also get the `check_profanity_text` tool to filter user inputs automatically. By running these checks directly inside your agent loop, you prevent inappropriate text from reaching your core LLM, allowing you to trace the exact moderation state in your OpenAI dashboard.

Targeted web scraping using natural language

The `ai_web_scrape` tool extracts clean data from raw web pages based on simple English prompts. Your OpenAI Agents SDK can query arbitrary URLs and receive structured text back without you writing custom selectors or maintenance-heavy parser scripts — and it doesn't break when layouts change. Combine this with `ai_web_search` to let your agent crawl the live web for fresh data. This setup lets your agent make decisions based on real-time search results, feeding the retrieved context directly into your OpenAI tracing dashboard using this MCP setup.

Extract and translate text on the fly

The `extract_text_from_image` tool pulls raw text from any online image URL using visual OCR. Your OpenAI Agents SDK handles the extraction, letting you pass the output to the next specialized agent in your handoff chain. You can then use `translate_text` to localize that extracted text immediately. The agent translates content across languages while maintaining the original meaning, all within a single execution step.

Setup guide

Set up JigsawStack 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 JigsawStack tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip first. Then initialize `MCPServerStreamableHttp` using the Vinkius endpoint URL. The SDK auto-discovers all seven tools from the MCP Server.

Yes, it does. Set `cacheToolsList=True` in your configuration to avoid fetching the tool definitions on every single agent run, which shaves off latency.

Yes, absolutely. You can have a routing agent use `check_profanity_text` to inspect inputs, then hand off clean data to a translation agent that uses `translate_text`.

If `extract_text_from_image` gets a broken URL, it returns a clear error string. Your agent catches this failure in the tracing dashboard and can try an alternative URL.

All images sent to `check_nsfw_image` and text sent to `summarize_text` are processed in ephemeral memory. Vinkius runs the MCP Server in a zero-trust sandbox, meaning your raw files and strings are never stored or used for model training.

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