How to Use the Coassemble MCP in OpenAI Agents SDK

Q: How do I configure Coassemble with the OpenAI Agents SDK?

Instantiate MCPServerStreamableHttp pointing to your Vinkius endpoint. This registers the MCP Server directly with your agent. Pass that instance into the mcpservers list when initializing your agent.

Get production OpenAI Agents SDK pipelines to enroll students and track Coassemble course progress with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coassemble MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Guardrails on OpenAI Agents SDK Student Enrollments

The `enroll_member_in_course` tool lets your autonomous Python agents safely register users into training tracks without human supervision. By exposing the function as an MCP tool, the OpenAI Agents SDK validates the action against your defined guardrails before writing any data to your LMS. If an agent tries to enroll someone who is not in your system, the framework catches the error during the pre-execution trace. You get clean, validated execution because the tool schema maps directly to your agent's function definitions.

Track Student Progress with Multi-Agent Handoffs

By calling `get_training_completion_results`, your agents can split the work of monitoring course completion between specialized systems. One agent can watch for new completions while another updates your external CRM with the latest scores. This MCP Server lets your agents pass context back and forth using native OpenAI framework handoffs. Your billing agent only triggers after the training agent confirms the user finished all required modules.

Audit Workspace Groups and Course Lists Dynamically

Using `list_coassemble_groups` and `list_coassemble_members` lets your system inspect what's happening inside your workspace on the fly. No more manual audits to check which student belongs where. Your agents query active classes with `list_coassemble_courses` to build fresh, context-aware training recommendations for your team. This setup avoids hardcoded IDs entirely.

Setup guide

Set up Coassemble 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 Coassemble tools at runtime.
3

Create your Agent

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

Run the agent

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

Instantiate `MCPServerStreamableHttp` pointing to your Vinkius endpoint. This registers the MCP Server directly with your agent. Pass that instance into the `mcp_servers` list when initializing your agent.

Yes. Your Python agent can loop through a list of users and call `enroll_member_in_course` for each one. Guardrails in the SDK ensure the loop halts if an invalid email format is detected.

Yes, every action is traced on your OpenAI developer dashboard. You can watch exactly when the agent calls the MCP tools to query `get_course_training_details`.

Yes. You can configure the server setup or limit the tools exposed to the agent constructor to only allow reading data like `list_coassemble_enrolments` while blocking modification tools.

All requests pass through a V8 isolate sandbox on Vinkius, meaning your LMS credentials never leak to the client side. Your student grades and email lists are processed in ephemeral memory and never stored by the gateway.

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