How to Use the Atlassian Crowd MCP in OpenAI Agents SDK

Provision users and manage Crowd directories safely inside your production-grade OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Atlassian Crowd MCP to OpenAI Agents SDK

Create your Vinkius account to connect Atlassian Crowd 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 Atlassian Crowd with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate user onboarding with OpenAI Agents SDK

This MCP server exposes direct user provisioning via `create_new_user` directly to your production agents. Your agent takes raw onboarding forms, extracts the required attributes, and hits the Atlassian API without intermediate glue code. Built-in guardrails in the SDK validate the payload before execution. If an agent tries to create a duplicate or malformed profile, the SDK catches the error before hitting your Crowd directory, logging the event in your OpenAI dashboard.

Audit group access on the fly

This MCP Server exposes tools like `list_user_memberships` and `get_user_details` to verify who has access to what. Security audits run automatically as your agent scans user profiles, checks active groups, and flags anomalies. When building multi-agent systems, one specialized agent pulls the raw group list using `list_all_groups` and hands off the evaluation to a security agent. You get full visibility of this handoff and execution trace in your central dashboard.

Query directories using precise filter strings

The server translates natural language queries into exact directory lookups using `search_users_by_attribute` and `search_users_by_name`. Instead of manual database lookups, the agent converts a request like finding all contractors added last week into a clean CQL-like restriction string. This eliminates broad database dumps. Rather than fetching the entire directory, the agent targets specific subsets, reducing latency and keeping your token usage low.

Setup guide

Set up Atlassian Crowd 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 Atlassian Crowd tools at runtime.
3

Create your Agent

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

Run the agent

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

You instantiate the server streamable HTTP class with your unique Vinkius endpoint. Pass this server instance inside the agent constructor using the mcp_servers list parameter. The SDK automatically discovers all ten directory management tools at runtime.

Yes, your agent can inspect and modify security groups directly. It uses tools like list_all_groups and get_group_details to read the current state before making any directory modifications.

The SDK handles rate limits by relying on OpenAI's built-in execution tracing and retry logic. If the Crowd API responds with a rate limit error, the agent pauses and retries the operation based on your backoff configuration.

The search tools return an empty list payload instead of throwing an error. Your agent reads this empty state and can immediately proceed to alternate search queries or log the missing record.

Your Crowd directory user data and active API tokens never leave your local environment. The server processes all user profiles and group memberships within a secure, ephemeral V8 isolate sandbox. No directory credentials are ever stored on Vinkius servers.

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