How to Use the AI21 Studio MCP in CrewAI

Q: How do I give CrewAI agents access to AI21 Studio?

Install crewaitools via pip. Add the Vinkius URL to the mcps parameter when defining your agent. The framework handles the rest.

Q: Can I restrict which AI21 Studio tools a CrewAI agent sees?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give one agent grammarcorrections and another agent embedtexts.

Equip your CrewAI agents with AI21 Studio Jamba models and text manipulation tools for autonomous research.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI21 Studio MCP to CrewAI

Create your Vinkius account to connect AI21 Studio 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 Studio with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized AI21 Studio Agents in CrewAI

You do not want one CrewAI agent handling every AI21 text operation. Assign the `chat_completion` tool to a dedicated reasoning agent powered by Jamba models. Then, give a separate editor agent access to the `grammar_corrections` tool. CrewAI lets these agents pass data back and forth. The researcher pulls raw text, the editor cleans it up, and a final compiler agent uses `summarize` to build the final report.

Autonomous Document Structuring via MCP

Messy input data stalls autonomous AI21 operations. Your formatting agent can call `segmentation` to break giant text blocks into clean, processable sentences. If the tone is wrong, another agent triggers `paraphrase`. You configure the tool for formal or casual styles depending on the target audience. The crew handles the formatting without you writing a single regex.

Vector Generation for Memory

CrewAI agents need vector embeddings to recall past actions. Connect the `embed_texts` tool so your crew can generate embeddings for their own outputs. They specify whether the text is a document to store or a query to search. Vinkius manages the authentication. You pass the endpoint URL directly into the mcps array in your setup. The agents authenticate once and run for hours.

Setup guide

Set up AI21 Studio 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 Studio tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install crewai[tools] via pip. Add the Vinkius URL to the mcps parameter when defining your agent. The framework handles the rest.

Yes. Use MCPServerHTTP from crewai.mcp and apply a tool_filter. You can give one agent grammar_corrections and another agent embed_texts.

Your crew can execute tasks in a strict order. An agent calls text_completion first, then passes the result to the next agent for processing.

The server exposes the full Jamba 1.5 family through the chat completion tools. Your agents can select large or mini variants based on task complexity.

Your proprietary research files and agent memory logs pass through a strict V8 isolate sandbox. The environment is ephemeral and retains zero state after the transaction.

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