How to Use the Mela MCP in OpenAI Agents SDK

Q: How do I configure OpenAI Agents SDK with the Mela MCP Server?

Install openai-agents via pip and configure the streamable HTTP transport with your endpoint token. Pass the server instance directly into your Agent constructor using the mcpservers argument. The SDK automatically discovers all 12 tools.

Q: What is the performance impact of auto-discovering Mela tools?

It is negligible if you enable tool caching. Set cacheToolsList=True in your SDK configuration to prevent repeated HTTP requests. Your agent will fetch the tool definitions once and run them instantly.

Get production-grade, validated on-site logs directly from your OpenAI Agents SDK workflows running Mela.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mela MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate site updates in OpenAI Agents SDK

This integration connects `log_work_hours` and `log_materials` to your OpenAI Agents SDK runtime for direct on-site data entry via MCP. Guardrails in the OpenAI SDK validate every hour logged and material entered before writing to your Mela database. You avoid bad inputs on your job sites without writing custom validation code. When field workers report progress, the OpenAI agent verifies the quantities against your Mela project rules. If a worker inputs 100 hours for a single day, the OpenAI SDK-level guardrails block the Mela write call and ask for correction. It keeps your field logs clean without manual oversight.

Let specialized agents run job costing

The MCP Server exposes `get_accounting_data` and `update_activity_status` to enable agent-to-agent handoffs. A scheduling agent tracks the project status, then hands off to an OpenAI financial agent to check the Mela budget. This keeps your bookkeeping synced with real-world progress. OpenAI's tracing dashboard tracks this entire Mela tool execution chain. You see exactly when the supervisor agent called `update_activity_status` and when the billing agent pulled the Mela accounting numbers. No black boxes, just clear step-by-step execution.

Post automated updates to Mela feeds

Your OpenAI agent uses `post_message` and `list_users` to coordinate field teams directly from Python. When a Mela job site runs low on materials, the agent identifies the correct team member and posts an alert. It replaces manual messages with automated, context-aware site updates. Because the Vinkius server runs in a secure V8 sandbox, your Mela team directory remains safe from rogue agent loops. The OpenAI agent only accesses the specific workspace data needed to run the tools. You get automated messaging without risking your employee directory.

Setup guide

Set up Mela 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 Mela tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip and configure the streamable HTTP transport with your endpoint token. Pass the server instance directly into your Agent constructor using the `mcp_servers` argument. The SDK automatically discovers all 12 tools.

Yes, that is the main reason to use this SDK. You define guardrails on the agent level to intercept calls to `log_work_hours` or `log_materials` before they reach the server. This prevents bad data from hitting your project feeds.

You set up specialized agents for different tasks, like one for checking budgets and another for posting messages. The SDK handles the transition, passing context from `get_accounting_data` to a financial agent automatically.

It is negligible if you enable tool caching. Set `cacheToolsList=True` in your SDK configuration to prevent repeated HTTP requests. Your agent will fetch the tool definitions once and run them instantly.

The SDK communicates with our secure V8 sandbox, which isolates your project logs and member lists. Only authorized tool calls like `get_me` execute, and no raw data is stored. Your API tokens are managed securely outside the runtime.

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