SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Jev MCP with Mastra AI

Connect Mastra AI to Jev MCP. List available jev models and versions, run a noul evaluation on model-x, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Jev logoJev
Api Key

Jev is TypeSafe AI's System One API for discovering models and evaluating structured state. Use it to run Noul, Choice, and Score structured evaluations with strong typing.

2 Tools

Introduction

This guide walks you through connecting Jev to Mastra AI using the Composio tool router. By the end, you'll have a working Jev agent that can discover available models, evaluate your structured state, run noul assessments, and ask choice and score questions through natural language commands.

This guide will help you understand how to give your Mastra AI agent real control over a Jev account through Composio's Jev MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Jev with

Claude CodeCursorChatGPTClaude CoworkOpenAI Agents SDKGrok BotCodexKimi CodeOpenCodeHermesAtomic AgentPiDeepSeek Harness

TL;DR

Here's what you'll learn:
  • Set up your environment so Mastra, OpenAI, and Composio work together
  • Create a Tool Router session in Composio that exposes Jev tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Jev tool definitions and attach them as a toolset
  • Build a Mastra agent that can reason, call tools, and return structured results
  • Run an interactive CLI where you can chat with your Jev agent

What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.

Key features include:

  • MCP Client: Built-in support for Model Context Protocol servers
  • Toolsets: Organize tools into logical groups
  • Step Callbacks: Monitor and debug agent execution
  • OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

What is the Jev MCP server, and what's possible with it?

The Jev MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Jev account. It provides structured and secure access to available Jev models and state evaluation, so your agent can discover models, evaluate shared state, ask named Noul, Choice, or Score questions, and assess multiple questions in parallel on your behalf.

  • Model discovery: Have your agent list the Jev models and aliases available to your account before choosing one for an evaluation.
  • Structured state evaluation: Direct your agent to evaluate a shared state using clearly named questions that fit your decision task.
  • Flexible question formats: Instruct your agent to use Noul, Choice, or Score questions based on the kind of assessment you need.
  • Parallel assessments: Let the agent evaluate several named questions against the same state in parallel to gather related results in one request.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Node.js 18 or higher
  • A Composio account with an active API key
  • An OpenAI API key
  • Basic familiarity with TypeScript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key.
  • You need credits or a connected billing setup to use the models.
  • Store the key somewhere safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Jev through MCP.
3

Install dependencies

bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv

Install the required packages.

What's happening:

  • @composio/core is the Composio SDK for creating MCP sessions
  • @mastra/core provides the Agent class
  • @mastra/mcp is Mastra's MCP client
  • @ai-sdk/openai is the model wrapper for OpenAI
  • dotenv loads environment variables from .env
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio
  • COMPOSIO_USER_ID tells Composio which user this session belongs to
  • OPENAI_API_KEY lets the Mastra agent call OpenAI models
5

Import libraries and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey as string,
});
What's happening:
  • dotenv/config auto loads your .env so process.env.* is available
  • openai gives you a Mastra compatible model wrapper
  • Agent is the Mastra agent that will call tools and produce answers
  • MCPClient connects Mastra to your Composio MCP server
  • Composio is used to create a Tool Router session
6

Create a Tool Router session for Jev

typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["jev"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Jev MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "jev" for Jev access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to
7

Configure Mastra MCP client and fetch tools

typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
What's happening:
  • MCPClient takes an id for this client and a list of MCP servers
  • The headers property includes the x-api-key for authentication
  • getTools fetches the tool definitions exposed by the Jev toolkit
8

Create the Mastra agent

typescript
const agent = new Agent({
    name: "jev-mastra-agent",
    instructions: "You are an AI agent with Jev tools via Composio.",
    model: "openai/gpt-5",
  });
What's happening:
  • Agent is the core Mastra agent
  • name is just an identifier for logging and debugging
  • instructions guide the agent to use tools instead of only answering in natural language
  • model uses openai("gpt-5") to configure the underlying LLM
9

Set up interactive chat interface

typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\n");

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        jev: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    console.log("\nSession ended.");
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Jev toolsets
  • maxSteps limits how many tool calls the agent can take in a single run
  • onStepFinish is a hook that prints intermediate steps for debugging

Complete Code

Here's the complete code to get you started with Jev and Mastra AI:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({ apiKey: composioAPIKey as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["jev"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      jev: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "jev-mastra-agent",
    instructions: "You are an AI agent with Jev tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { jev: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();

Conclusion

You've built a Mastra AI agent that can interact with Jev through Composio's Tool Router. You can extend this further by:
  • Adding other toolkits like Gmail, Slack, or GitHub
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows
TOOLS

Supported Tools

Every Jev action and event your agent gets out of the box.

Evaluate State

Evaluate one shared state against one or more named Noul, Choice, or Score questions in parallel; each call performs usage-priced inference.

List Models

List the Jev model names and aliases available to the connected account for use in evaluations.

FRAMEWORKS

How to build Jev MCP Agent with another framework

Claude Code logo

Claude Code

Use Jev MCP with Claude Code

Cursor logo

Cursor

Use Jev MCP with Cursor

ChatGPT logo

ChatGPT

Use Jev MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Jev MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Jev MCP with OpenAI Agents SDK

Grok Bot logo

Grok Bot

Use Jev MCP with Grok Bot

Codex logo

Codex

Use Jev MCP with Codex

Kimi Code logo

Kimi Code

Use Jev MCP with Kimi Code

OpenCode logo

OpenCode

Use Jev MCP with OpenCode

Hermes logo

Hermes

Use Jev MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Jev MCP with Atomic Agent

Pi logo

Pi

Use Jev MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Jev MCP with DeepSeek Harness

FAQ

Frequently asked questions

With a standalone Jev MCP server, the agents and LLMs can only access a fixed set of Jev tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Jev and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Mastra AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Jev tools.

Yes, absolutely. You can configure which Jev scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Jev data and credentials are handled as safely as possible.

Start with Jev.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Jev tool your agent needs.Free to start.

Start building