How to Use the MonkeyLearn MCP in CrewAI

Q: How do I handle tool errors in CrewAI with MonkeyLearn?

You can add a monitor agent to your crew that checks getapistatus. If a service issue is detected, the monitor can alert your team or pause the execution.

Deploy autonomous research and analysis crews with MonkeyLearn and CrewAI, featuring agent-based collaboration and task automation.

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 CrewAI

Create your Vinkius account to connect MonkeyLearn to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized agent analysis

Assign a dedicated agent to run `classify_text` on incoming feedback. It operates as a member of your crew, processing data independently of other tasks. Your agents handle the heavy lifting while you define the overall mission. It creates a clear separation between the analysis agent and the response agent.

Automated entity research

Use `extract_text_entities` to let your research agent identify patterns in large datasets. It feeds the findings to the rest of the crew for further action. The tool outputs are structured, making it easy for the next agent in the sequence to understand the context. It removes manual data entry from your operations.

Versioned model execution

Call `list_model_versions` to ensure your crew is using the latest trained classifier. It keeps your agents aligned with your current business taxonomy. You control the model updates while the agents handle the execution. It prevents accuracy drift by keeping your agents locked to the correct model version.

Setup guide

Set up MonkeyLearn MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke MonkeyLearn tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="MonkeyLearn Analyst",
    goal="Access and analyze MonkeyLearn data via MCP.",
    backstory="Expert analyst with direct MonkeyLearn access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent MonkeyLearn transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="MonkeyLearn Analyst",
        goal="Access and analyze MonkeyLearn data via MCP.",
        backstory="Expert analyst with direct MonkeyLearn access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent MonkeyLearn transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL to the agent's MCP configuration. You can then selectively expose tools like `classify_text` to specific agents based on their assigned role.

Yes, you can define the MCP server globally so all agents in the crew have access to the tools. This allows for shared memory and collaborative analysis.

You can add a monitor agent to your crew that checks `get_api_status`. If a service issue is detected, the monitor can alert your team or pause the execution.

Absolutely, have one agent perform the research and a second agent run `run_workflow` to extract insights. It creates a robust, multi-step analysis pipeline.

The text is processed within the scope of your agent task. We ensure the connection is strictly point-to-point, keeping your sensitive customer feedback isolated.

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