How to Use the JSON Path Query Engine MCP in OpenAI Agents SDK

Q: How does the JSON Path Query Engine work with the OpenAI Agents SDK?

The engine exposes a queryjson tool that your agent can call. The OpenAI Agents SDK automatically discovers this tool from the MCP Server, allowing it to run JSONPath queries against large data payloads without needing custom code.

Q: Can I trace queries from the JSON Path Query Engine in my OpenAI Agents SDK dashboard?

Yes. Every call to queryjson appears in your agent's trace. You'll see the exact JSONPath expression used and the data returned, which makes debugging agent behavior much easier.

Q: What data does this server see when I use it?

The server processes the raw JSON string and the JSONPath expression you provide. Vinkius runs each request in an ephemeral, zero-trust sandbox. The data is only held in memory for the duration of the query and is immediately discarded.

Extract data from huge JSON payloads without breaking your OpenAI Agents SDK production guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JSON Path Query Engine MCP to OpenAI Agents SDK

Create your Vinkius account to connect JSON Path Query Engine 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 JSON Path Query Engine with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Big JSON, Get Small Answers

The `query_json` tool lets your agent pull just the data it needs from a massive JSON string. Instead of feeding a whole API response into the context, you pass the raw JSON and a JSONPath expression like `$.users[*].email`. It returns only the matching values. This keeps your token count low and your agent's focus sharp. For the OpenAI Agents SDK, it means your guardrails have less surface area to validate, and handoffs between specialized agents are faster because the data payloads are tiny and targeted.

Cut Token Costs and Latency

Sending large JSON objects to your model costs money and adds time. The `query_json` tool runs on the server, offloading the parsing and filtering work before the data ever hits your agent. Your agent asks for what it wants, gets a small result, and moves on. You'll see the difference in your OpenAI dashboard tracing. Instead of a huge, unreadable JSON blob in the logs, you'll see a clean, targeted query and a concise response. This makes debugging and performance tuning way simpler.

Auto-Discovery for your MCP Server

Your OpenAI Agent discovers the `query_json` tool automatically. Just point it to the Vinkius MCP Server endpoint. There's no manual tool registration or schema definition needed on your side. Set `cacheToolsList=True` in your agent's constructor for even better performance on subsequent runs. The agent fetches the tool list once and then gets straight to work, using `query_json` to pull data without any extra setup.

Setup guide

Set up JSON Path Query Engine 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 JSON Path Query Engine tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate JSON Path Query Engine 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="JSON Path Query Engine Agent",
            instructions="You have access to JSON Path Query Engine 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 jsonpath-plus. 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 JSON Path Query Engine 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 JSON Path Query Engine MCP in OpenAI Agents SDK

The engine exposes a `query_json` tool that your agent can call. The OpenAI Agents SDK automatically discovers this tool from the MCP Server, allowing it to run JSONPath queries against large data payloads without needing custom code.

It prevents you from loading multi-megabyte JSON files into your agent's memory, which can cause crashes. The server handles the heavy lifting, so your agent only deals with the small, specific data it actually needs.

Yes. Every call to `query_json` appears in your agent's trace. You'll see the exact JSONPath expression used and the data returned, which makes debugging agent behavior much easier.

It supports standard JSONPath syntax. This includes deep selectors, wildcards, and filter expressions, like `$.store.book[?(@.price < 10)]`. Your agent can construct these queries dynamically to find exactly what it needs.

The server processes the raw JSON string and the JSONPath expression you provide. Vinkius runs each request in an ephemeral, zero-trust sandbox. The data is only held in memory for the duration of the query and is immediately discarded.

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