How to Use the Jiminny MCP in OpenAI Agents SDK

Q: How do I connect Jiminny to my OpenAI Agents SDK?

Install the SDK and register the Jiminny MCP Server using MCPServerStreamableHttp. Pass the server object directly into your Agent constructor to let your agent auto-discover the tools.

Q: Can OpenAI Agents SDK handle Jiminny transcripts securely?

Yes, the SDK processes gettranscript data within your configured environment parameters. It uses OpenAI's built-in guardrails to validate every tool execution before it runs.

Q: Does the OpenAI Agents SDK support caching for Jiminny tools?

Yes, setting cacheToolsList=True in your SDK configuration improves performance when fetching Jiminny tools. This reduces startup latency for your production agents.

Q: How do agents fetch user details?

Your agent invokes getuser to pull specific profile details from your Jiminny account. This helps map coaching metrics to the correct team member.

Build production-ready OpenAI Agents SDK systems that analyze sales calls using Jiminny data with built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jiminny MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze call details with OpenAI Agents SDK

Your agent runs `get_transcript` and `get_action_items` to pull raw conversation data directly into your OpenAI Agents SDK runtime using this MCP Server. Instead of guessing what happened on a sales call, the agent reads the exact dialogue and extracts commitments made by the rep or customer. This setup uses the SDK's native guardrails to ensure your agent doesn't execute unauthorized Jiminny API calls. By passing the server to the agent constructor, your system gets direct access to raw Jiminny conversation records without manual token parsing.

Track sales performance via OpenAI Agents SDK

Your agent uses `get_coaching_stats` and `get_call_stats` to identify which reps need immediate attention based on hard data. The SDK handles handoffs between specialized agents, letting one agent fetch Jiminny team metrics while another analyzes individual coaching. This MCP Server connects your OpenAI dashboard directly to Jiminny team structures. You can trace every tool call like `list_teams` or `list_users` to see exactly how your agent queries your organization's hierarchy.

Verify connection status in production pipelines

Before running complex multi-agent workflows, your OpenAI Agents SDK system runs `check_jiminny_status` over the MCP connection to confirm the API is responsive. This prevents broken runs and saves API credits by catching connectivity issues early. Once verified, the agent safely runs `list_activities` and `get_activity` to map out recent sales meetings. The entire process is logged inside your OpenAI dashboard for complete visibility.

Setup guide

Set up Jiminny 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 Jiminny tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and register the Jiminny MCP Server using `MCPServerStreamableHttp`. Pass the server object directly into your Agent constructor to let your agent auto-discover the tools.

Yes, the SDK processes `get_transcript` data within your configured environment parameters. It uses OpenAI's built-in guardrails to validate every tool execution before it runs.

Yes, setting `cacheToolsList=True` in your SDK configuration improves performance when fetching Jiminny tools. This reduces startup latency for your production agents.

Your agent invokes `get_user` to pull specific profile details from your Jiminny account. This helps map coaching metrics to the correct team member.

Your sales call transcripts and coaching metrics are processed in an ephemeral V8 sandbox. Vinkius handles the authorization token securely, so your OpenAI Agents SDK never exposes raw credentials to the LLM.

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