How to Use the MonkeyLearn MCP in OpenAI Agents SDK

Q: How do I connect the MonkeyLearn MCP server to my OpenAI Agents SDK project?

Install the package using pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius URL. Pass this server instance into the mcpservers list when constructing your agent. The SDK handles tool discovery automatically.

Q: How does OpenAI Agents SDK trace requests sent to MonkeyLearn?

Every call to classifytext or getclassifierdetails appears in your OpenAI developer dashboard timeline. You can inspect the exact payload sent and the classification tags returned for every single run.

Q: What happens if a workflow is updated on the platform?

Use listworkflows to fetch the updated automated pipelines at runtime. This keeps your agent in sync with your team's latest manual changes without restarting your Python process.

Parse raw text into structured categories directly inside your OpenAI Agents SDK pipeline without manual post-processing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MonkeyLearn MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Classify tickets instantly with OpenAI Agents SDK MCP Server.

The `classify_text` tool sends your raw incoming support strings directly to your custom MonkeyLearn classification models. Your OpenAI Agents SDK pipeline receives structured tags like sentiment or topic without requiring manual prompt engineering. We run this inside the OpenAI execution loop, letting you trigger specific agent handoffs based on the returned category. If the category is billing, the main coordinator route hands off the conversation to your specialized finance agent instantly.

Pull structured entities from unstructured text.

The `extract_text` tool identifies specific keywords, emails, or product names from raw text payloads. This tool feeds clean JSON directly back into your OpenAI Agents SDK environment for immediate action. You get clean variables to pass down to subsequent steps instead of relying on fragile LLM extraction. Preventing hallucinations during database writes keeps your production data clean.

Sync tag hierarchies with your agent tools.

The `list_tag_trees` tool fetches your current classification categories and hierarchies directly from your account. Your OpenAI Agents SDK system queries this endpoint to dynamically update its internal routing options. Using this tool avoids hardcoding label lists in your system prompts. When you update a tag in your dashboard, your agent instantly adapts to the new categories on its next run.

Setup guide

Set up MonkeyLearn 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 MonkeyLearn tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius URL. Pass this server instance into the `mcp_servers` list when constructing your agent. The SDK handles tool discovery automatically.

Yes, you can define validation rules that inspect arguments before they reach `classify_text` or `extract_text`. This setup ensures your agent never sends empty payloads or malformed text to the API.

Every call to `classify_text` or `get_classifier_details` appears in your OpenAI developer dashboard timeline. You can inspect the exact payload sent and the classification tags returned for every single run.

Use `list_workflows` to fetch the updated automated pipelines at runtime. This keeps your agent in sync with your team's latest manual changes without restarting your Python process.

This integration processes your raw text data within an ephemeral V8 sandbox before sending it to the API. No text payloads are stored on the Vinkius gateway, ensuring your customer logs remain strictly private.

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