How to Use the Jibble MCP in OpenAI Agents SDK

Q: How do I configure the Jibble MCP server within the OpenAI Agents SDK?

Install openai-agents via pip and initialize the server using MCPServerStreamableHttp with your unique Vinkius endpoint. Pass this server instance inside the mcpservers list when constructing your agent to auto-discover all ten tracking tools.

Q: What is the best way to trace tool execution in this setup?

You can monitor every single call to listactivities or listprojects directly on your OpenAI developer dashboard. The platform provides full execution traces, showing the exact payloads sent to the server and the raw responses returned.

Q: How does this MCP Server secure sensitive employee location data?

All geographic coordinates retrieved via listlocations are processed within ephemeral V8 isolates on Vinkius. Your private tracking data, including individual employee names from listpeople, is never stored or used for model training.

Deploy autonomous OpenAI Agents SDK workflows that manage Jibble time logs and verify organization settings 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 Jibble MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Log Audits via OpenAI Agents SDK

You can now let your OpenAI-driven workforce agents inspect individual work hours without manual oversight. By exposing `get_time_entry` via this MCP Server directly to your multi-agent system, the primary agent can flag anomalies in location data or activity notes and coordinate with a supervisor agent to resolve discrepancies. This setup relies on the SDK's native handoff architecture to pass the validated context between specialized agents. If a worker logged hours outside their assigned zone, the agent calls `list_locations` to cross-reference coordinates before writing any correction back to the system.

Align project allocations with live team structures

Managing contractor hours across multiple client accounts usually requires constant dashboard hopping. This Jibble MCP integration lets your agents run `list_projects` alongside `list_clients` to automatically calculate billable hours against active contracts. The agent pulls live rosters using `list_people` to verify that only authorized team members are booking hours to high-priority client codes. You get clean, pre-audited project reports delivered straight to your billing pipeline without writing custom data-sync scripts.

Enforce organization compliance at runtime

Before executing any complex personnel changes, your agent needs to know it is working with the correct account parameters. Running `get_organization` allows the agent to verify account-wide configurations and tax settings instantly. This prevents the agent from making incorrect assumptions when querying `list_groups` to organize remote workers or sales teams. It establishes a reliable baseline so your autonomous scripts never push updates to the wrong corporate entity.

Setup guide

Set up Jibble 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 Jibble tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip and initialize the server using `MCPServerStreamableHttp` with your unique Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when constructing your agent to auto-discover all ten tracking tools.

Yes, you can define safety parameters directly in your Python code to restrict which tools the agent can execute. For instance, you can allow the agent to run `list_time_entries` for reporting while blocking it from accessing sensitive personnel details via `get_person`.

The SDK lets you implement custom retry logic and backoff strategies within your async context manager. When pulling massive datasets using `list_time_entries`, the agent handles rate limits gracefully without dropping the connection.

You can monitor every single call to `list_activities` or `list_projects` directly on your OpenAI developer dashboard. The platform provides full execution traces, showing the exact payloads sent to the server and the raw responses returned.

All geographic coordinates retrieved via `list_locations` are processed within ephemeral V8 isolates on Vinkius. Your private tracking data, including individual employee names from `list_people`, is 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