How to Use the Chord Constructor MCP in OpenAI Agents SDK

Q: What is the best way to use Chord Constructor with OpenAI Agents SDK?

Start by letting your agent run parsechordstring on a passage you care about. This creates a clean dataset of notes, which your agent can then pass along to other tools for analysis.

Build complex music theory agents using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chord Constructor MCP to OpenAI Agents SDK

Create your Vinkius account to connect Chord Constructor 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 Chord Constructor with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze chord function in any key

The `determine_harmonic_role` tool pinpoints a chord's functional place within a given musical scale. You tell your agent the key, and it tells you if that chord acts as a subdominant or a dominant. This is critical for knowing how to build tension into a piece. It goes beyond just naming chords; it maps their purpose relative to the tonal center. If an agent needs to write music that resolves correctly, this function gives it the structural roadmap it needs.

Deconstruct complex chord notation

Start by using `parse_chord_string` to turn raw chord names into structured data. This tool takes a messy string like 'Cmaj7/G' and accurately breaks down the root, intervals, and normalized name components. It makes sure your agent isn't guessing what the user actually meant. This parsing ability is fundamental for any advanced musical workflow. You feed it notation, and it returns clean, usable data points that other tools can read immediately.

Define precise chord voicings

Need to know how a chord should sound when played? The agent uses `generate_voicings` to return specific note arrangements. You can ask it for 'open' or 'closed' textures, getting back structured data that tells you exactly where every note needs to land. It also figures out all the possible permutations using `get_chord_inversions`, calculating every way a chord can be voiced while changing which note acts as the bass. This gives your agent total control over texture.

Setup guide

Set up Chord Constructor 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 Chord Constructor tools at runtime.
3

Create your Agent

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

Run the agent

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

The MCP lets your agent read and write structured musical data. You feed it a chord, and the agent uses internal functions to analyze its role or generate inversions. It's all done through one unified endpoint.

Start by letting your agent run `parse_chord_string` on a passage you care about. This creates a clean dataset of notes, which your agent can then pass along to other tools for analysis.

Yes. The system handles advanced harmonic decomposition by identifying functional roles and calculating precise inversions based on the input chord symbols.

Absolutely. You can have your agent take the output from a voicing tool, use that data to determine harmonic function, and then write a final musical directive based on both results.

This MCP handles structural musical theory components, specifically reading and processing raw musical chord symbols and their resulting structured note intervals.

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