How to Use the AI21 Labs MCP in Mastra AI

Q: How do I add AI21 Labs tools to a Mastra AI agent via the MCP Server?

Instantiate the MCPClient with your Vinkius URL in your Mastra config. Spread the returned tools into your agent's tool array so it can immediately access Jamba completions.

Q: How do I require approval before Mastra AI runs an AI21 Labs delete tool?

Set requireToolApproval to true for ai21deletefile in your Mastra agent configuration. The agent will pause and wait for your explicit permission before removing any uploaded context file.

Q: Does Mastra AI support the semantic segmentation tools?

Absolutely. Your Mastra agent can call ai21segmenttext to split long transcripts, then pass those segments to subsequent steps in your workflow graph.

Q: How is my file data protected when Mastra AI calls this server?

All file metadata and raw contents processed by ai21getfile run inside our secure MCP sandbox. Every Mastra session is ephemeral, meaning your uploaded files are completely wiped from our infrastructure the millisecond the execution finishes.

Build resilient, multi-step text workflows in Mastra AI with direct access to Jamba-1.5 models via 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 Mastra AI

Create your Vinkius account to connect AI21 Labs to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build self-healing document pipelines in Mastra AI.

The `ai21_summarize_text` and `ai21_segment_text` tools break down massive documents into structured, topical chapters. If a step fails, Mastra's workflow engine triggers a backoff retry automatically. You define the execution graph in TypeScript, mapping the output of the Jamba summarizer straight into your database. The system handles transient network drops without crashing your ingest pipeline.

Automate copy editing with human-in-the-loop approvals.

The `ai21_paraphrase_text` tool generates multiple variations of your marketing copy based on your workflow rules. Mastra AI halts the sequence and requests admin approval before publishing any variation. You get total control over the Jamba output quality. The workflow stays paused until a human clicks approve, then resumes to push the final copy to production.

Manage remote files securely inside your Mastra agents.

The `ai21_list_files` and `ai21_delete_file` tools allow your agents to clean up their own workspace after processing jobs. You write Mastra workflow logic to purge old context files once a run finishes. This MCP Server setup keeps your storage footprint minimal. Your Mastra agents query the file list, identify stale data, and run deletions without manual intervention.

Setup guide

Set up AI21 Labs MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All AI21 Labs tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "ai21-labs-mcp-client",
  servers: {
    "ai21-labs-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "AI21 Labs Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to AI21 Labs tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent AI21 Labs transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the `MCPClient` with your Vinkius URL in your Mastra config. Spread the returned tools into your agent's tool array so it can immediately access Jamba completions.

Yes, Mastra's built-in workflow engine handles transient network errors by retrying the `ai21_chat_completion` tool with exponential backoff. You don't have to write custom error-handling loops.

Set `requireToolApproval` to true for `ai21_delete_file` in your Mastra agent configuration. The agent will pause and wait for your explicit permission before removing any uploaded context file.

Absolutely. Your Mastra agent can call `ai21_segment_text` to split long transcripts, then pass those segments to subsequent steps in your workflow graph.

All file metadata and raw contents processed by `ai21_get_file` run inside our secure MCP sandbox. Every Mastra session is ephemeral, meaning your uploaded files are completely wiped from our infrastructure the millisecond the execution finishes.

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