How to Use the AI21 Labs MCP in CrewAI

Q: How do I configure CrewAI agents to use the AI21 Labs MCP Server?

Pass your Vinkius HTTP endpoint to the mcps array when defining your CrewAI agents. The agents auto-discover tools like ai21chatcompletion and use them during their tasks.

Q: How do CrewAI agents manage files using the AI21 Labs tools?

Your CrewAI agents use ai21listfiles to scan available context documents, then download details using ai21getfile. They coordinate these actions using shared memory to avoid duplicate API requests.

Deploy collaborative crews that analyze, summarize, and edit text using AI21 Labs tools and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI21 Labs MCP to CrewAI

Create your Vinkius account to connect AI21 Labs 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 AI21 Labs with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent editing desks using this MCP Server.

The `ai21_grammar_correction` and `ai21_text_improvements` tools give your editor agents precise programmatic control over raw drafts. One agent drafts, while a second specialized agent refines the tone. CrewAI manages the handoff between these roles. The editing agent runs the Jamba improvement tool, compares the diff, and passes the polished copy to the publisher agent.

Ground your CrewAI research agents with verified context.

The `ai21_contextual_answers` tool ensures your research agents only answer questions using verified source documents. This prevents your autonomous teams from making up facts during deep-dive investigations. You assign a specific document context to the CrewAI agent's memory. The agent queries the Jamba tool, receives validated answers, and shares the structured findings with the rest of the crew.

Automate large-scale document analysis across agent teams.

The `ai21_summarize_text` and `ai21_segment_text` tools let your analyst agents digest massive text dumps in seconds. A researcher agent segments the document, while a writer agent summarizes each part. This collaborative approach avoids Jamba token limit bottlenecks. Your crew processes massive files by distributing the work across specialized roles, running sequentially or hierarchically.

Setup guide

Set up AI21 Labs 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 AI21 Labs tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="AI21 Labs Analyst",
    goal="Access and analyze AI21 Labs data via MCP.",
    backstory="Expert analyst with direct AI21 Labs access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent AI21 Labs 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="AI21 Labs Analyst",
        goal="Access and analyze AI21 Labs data via MCP.",
        backstory="Expert analyst with direct AI21 Labs access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AI21 Labs 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 AI21 Labs. 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 AI21 Labs 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 AI21 Labs MCP in CrewAI

Pass your Vinkius HTTP endpoint to the `mcps` array when defining your CrewAI agents. The agents auto-discover tools like `ai21_chat_completion` and use them during their tasks.

Yes, you can set up a CrewAI moderator agent to inspect the output of `ai21_chat_completion` before passing it to other agents. This ensures high-quality results across your entire autonomous run.

Your CrewAI agents use `ai21_list_files` to scan available context documents, then download details using `ai21_get_file`. They coordinate these actions using shared memory to avoid duplicate API requests.

Yes, configure the MCP tool filter in CrewAI to expose only specific tools like `ai21_summarize_text`. This keeps your agent focused and prevents accidental tool runs.

Absolutely. Your processed text and documents handled by CrewAI are isolated within ephemeral runtime environments. Vinkius secures the communication channel, ensuring that raw context files never leak to external environments.

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