How to Use the MonkeyLearn MCP in AutoGen

Q: How do I register the MonkeyLearn MCP Server with AutoGen agents?

Run pip install -U "autogen-extmcp" to install the extension. Then, use mcpservertools with your Vinkius HTTP URL and pass the tools directly to your AssistantAgent.

Q: Can AutoGen agents negotiate MonkeyLearn classification tags if they disagree?

Yes. One agent can call classifytext while another calls listclassifiertags to verify the tag options, allowing them to debate and reach a consensus on the correct label.

Q: How do AutoGen agents discover what MonkeyLearn extractors are available?

Agents call listextractors to retrieve the active list of extraction models. They then select the appropriate extractor based on the type of text they need to process.

Q: Can I use custom workflows within an AutoGen conversation?

Yes, your agents can call runworkflow to process text blocks. The resulting structured data is then shared back into the group chat for other agents to use.

Enable multi-agent debate and consensus on text classification using AutoGen and MonkeyLearn.

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 AutoGen

Create your Vinkius account to connect MonkeyLearn to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent debates on MonkeyLearn classifications

Your AutoGen agents use `classify_text` to independently analyze customer feedback. If a sentiment agent and a topic agent disagree on a classification, they debate the result using the raw confidence scores. It's worth noting how they resolve conflicts. This consensus-driven approach ensures high accuracy. By checking `get_classifier_details`, the supervisor agent weighs each agent's conclusion against the model's training parameters. They don't move forward until they agree.

Validate extracted entities with this MCP Server

This MCP Server provides `extract_text_entities` so your data extraction agent can pull critical fields from raw text. A separate validation agent then reviews these entities to ensure they meet your business rules. This prevents bad data from leaking into your pipeline. If the validation agent finds an anomaly, it calls `get_extractor_details` to verify the extraction rules. The agents negotiate until they agree on the final, cleaned data structure.

Coordinate complex NLP tasks across multiple agents

The `run_workflow` tool allows your coordinator agent to execute complex multi-step text processing. The agent then distributes the output parts to specialized sub-agents for downstream tasks. This breaks up heavy processing jobs. To manage this, your agents use `list_nlp_workflows` to discover available processing pipelines. They dynamically assign these pipelines to different steps of the conversation based on the task requirements.

Setup guide

Set up MonkeyLearn MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes MonkeyLearn tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="MonkeyLearn_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent MonkeyLearn data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="MonkeyLearn_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent MonkeyLearn data")
    print(result.messages[-1].content)

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 AutoGen

Run `pip install -U "autogen-ext[mcp]"` to install the extension. Then, use mcp_server_tools with your Vinkius HTTP URL and pass the tools directly to your AssistantAgent.

Yes. One agent can call `classify_text` while another calls `list_classifier_tags` to verify the tag options, allowing them to debate and reach a consensus on the correct label.

Agents call `list_extractors` to retrieve the active list of extraction models. They then select the appropriate extractor based on the type of text they need to process.

Yes, your agents can call `run_workflow` to process text blocks. The resulting structured data is then shared back into the group chat for other agents to use.

All conversational text and classification requests run in secure, ephemeral V8 isolates on Vinkius. Your data is encrypted in transit and never stored, ensuring complete privacy for your customer interactions.

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