How to Use the Leiga MCP in OpenAI Agents SDK

Q: Can I use multiple specialized agents with Leiga and OpenAI Agents SDK?

Yes, you can set up a triage agent that calls listprojects and then hands off to a writer agent. The writer agent then executes createtask to build out the specific sprint items.

Q: How do I cache tool definitions for Leiga in OpenAI Agents SDK?

Set cacheToolsList=True when initializing your connection. This stops the SDK from refetching the schemas for listworkflows and other tools on every single turn.

Q: What happens if an agent fails during a task update?

The OpenAI dashboard logs the exact payload sent to gettaskdetails. You can inspect the trace, fix the prompt, and retry the run without losing your place.

Run production-ready OpenAI Agents SDK setups that safely update your Leiga sprint backlogs without breaking your workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leiga MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run safe sprint audits with your OpenAI Agents SDK

This MCP Server uses the `list_tasks` tool to feed active ticket data directly into your OpenAI Agents SDK. Your agent scans the active sprint to spot bottlenecks before they stall your developers. Because OpenAI SDK handles agent handoffs, you can have one agent analyze capacity with `list_team_members` and another write the tickets. The built-in guardrails block bad assignments before they reach your live boards.

Automate ticket creation using OpenAI Agents SDK

Creating tickets with the `create_task` tool on this MCP Server becomes safer when your OpenAI Agents SDK validates the input against your team schemas. The agent verifies project parameters using `get_project_details` before writing a single line to your backlog. You track every single tool execution inside your OpenAI developer dashboard. If an agent tries to assign a task to a non-existent team, the run halts immediately, keeping your project board clean.

Map out team workloads with OpenAI Agents SDK

This MCP Server exposes `list_organizational_teams` so your OpenAI Agents SDK can audit capacity across your entire company. The agent cross-references these teams with `list_workflows` to see which groups are stuck on legacy pipelines. You get real-time Leiga resource mapping inside your OpenAI agent without manual spreadsheets. By running this check daily, your agent spots overloaded teams and logs detailed task updates using `get_task_details`.

Setup guide

Set up Leiga 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 Leiga tools at runtime.
3

Create your Agent

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

Run the agent

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

You configure the SDK context manager to catch API limits during high-volume operations. The agent pauses executions of `list_tasks` automatically when it detects throttle warnings from the server.

Yes, you can set up a triage agent that calls `list_projects` and then hands off to a writer agent. The writer agent then executes `create_task` to build out the specific sprint items.

Set `cacheToolsList=True` when initializing your connection. This stops the SDK from refetching the schemas for `list_workflows` and other tools on every single turn.

The OpenAI dashboard logs the exact payload sent to `get_task_details`. You can inspect the trace, fix the prompt, and retry the run without losing your place.

Your project data, including task descriptions and team names fetched by `list_team_members`, stays inside an isolated V8 sandbox. Vinkius uses single-use ephemeral environments, meaning no project details are stored on disk after your agent finishes its run.

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