How to integrate Jira MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Jira Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Jira to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Jira agent that can create a new bug in project alpha, assign issue jira-102 to sarah lee, add comment to ticket jira-207 with update, start a new sprint for the dev board through natural language commands.

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

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

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Jira integration
  • Using Composio's Tool Router to dynamically load and access Jira tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

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

The Jira MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Jira account. It provides structured and secure access to your Jira projects, so your agent can perform actions like creating issues, managing sprints, commenting on tasks, assigning work, and tracking releases on your behalf.

  • Automated issue creation and tracking: Let your agent create new bugs, tasks, or stories, and keep tabs on issues across your Jira projects.
  • Collaborative commenting and updates: Have your agent add rich-text comments or attachments to issues, keeping team communication seamless and up to date.
  • Effortless assignment and watcher management: Easily assign issues to teammates or add watchers, ensuring everyone stays in the loop and accountable.
  • Sprint and release planning: Empower your agent to create sprints, manage boards, and organize project milestones or versions for agile teams.
  • Issue linking and bulk operations: Direct your agent to link related issues or perform bulk creation of tasks, streamlining project workflows and dependencies.

Supported Tools & Triggers

Tools
Triggers
Add AttachmentUploads and attaches a file to a jira issue.
Add CommentAdds a comment using atlassian document format (adf) for rich text to an existing jira issue.
Add Watcher to IssueAdds a user to an issue's watcher list by account id.
Assign IssueAssigns a jira issue to a user, default assignee, or unassigns; supports email/name lookup.
Bulk Create IssuesCreates multiple jira issues (up to 50 per call) with full feature support including markdown, assignee resolution, and priority handling.
Create IssueCreates a new jira issue (e.
Link IssuesLinks two jira issues using a specified link type with optional comment.
Create ProjectCreates a new jira project with required lead, template, and type configuration.
Create SprintCreates a new sprint on a jira board with optional start/end dates and goal.
Create VersionCreates a new version for releases or milestones in a jira project.
Delete CommentDeletes a specific comment from a jira issue using its id and the issue's id/key; requires user permission to delete comments on the issue.
Delete IssueDeletes a jira issue by its id or key.
Delete VersionDeletes a jira version and optionally reassigns its issues.
Delete WorklogDeletes a worklog from a jira issue with estimate adjustment options.
Edit IssueUpdates an existing jira issue with field values and operations.
Find UsersSearches for jira users by email, display name, or username to find account ids; essential for assigning issues, adding watchers, and other user-related operations.
Get All Issue Type SchemesRetrieves all jira issue type schemes with optional filtering and pagination.
Get all projectsRetrieves all visible projects using the modern paginated jira api with server-side filtering and pagination support.
Get Issue StatusesRetrieves all available issue statuses from jira with details.
Get All UsersRetrieves all users from the jira instance including active, inactive, and other user states with pagination support.
Get CommentRetrieves a specific comment by id from a jira issue with optional expansions.
Get Current UserRetrieves detailed information about the currently authenticated jira user.
Get IssueRetrieves a jira issue by id or key with customizable fields and expansions.
Get Issue Link TypesRetrieves all configured issue link types from jira.
Get Issue PropertyRetrieves a custom property from a jira issue by key.
Get Issue ResolutionsRetrieves all available issue resolution types from jira.
Get issue typesRetrieves all jira issue types available to the user using the modern api v3 endpoint; results vary based on 'administer jira' global or 'browse projects' project permissions.
Get Issue Type SchemeGets a jira issue type scheme by id with all associated issue types.
Get Issue WatchersRetrieves users watching a jira issue for update notifications.
Get Issue WorklogsRetrieves worklogs for a jira issue with user permission checks.
Get Project VersionsRetrieves all versions for a jira project with optional expansion.
Get Issue Remote LinksRetrieves links from a jira issue to external resources.
Get TransitionsRetrieves available workflow transitions for a jira issue.
Get Issue VotesFetches voting details for a jira issue; requires voting to be enabled in jira's general settings.
Get WorklogsRetrieves worklogs for a specified jira issue.
List BoardsRetrieves paginated jira boards with filtering and sorting options.
List Issue CommentsRetrieves paginated comments from a jira issue with optional ordering.
List SprintsRetrieves paginated sprints from a jira board with optional state filtering.
Move Issues to SprintMoves one or more jira issues to a specified active sprint.
Remove Watcher from IssueRemoves a user from an issue's watcher list by account id.
Search Issues Using JQL (GET)Searches for jira issues using jql with pagination and field selection.
Search Issues Using JQL (POST)Searches for jira issues using jql via post request for complex queries; ideal for lengthy jql queries that might exceed url character limits
Search issuesAdvanced jira issue search supporting structured filters and raw jql.
Send Notification for IssueSends a customized email notification for a jira issue.
Transition IssueTransitions a jira issue to a different workflow state, with support for transition name lookup and user assignment by email.
Update CommentUpdates text content or visibility of an existing jira comment.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

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

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { experimental_createMCPClient as createMCPClient } from "@ai-sdk/mcp";

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

if (!process.env.OPENAI_API_KEY) 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,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const { session } = await composio.create(composioUserID!, {
    toolkits: ["jira"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Jira tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Jira-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Jira tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to jira, like summarize my last 5 emails, send an email, etc... :)))\n",
);

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

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
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({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

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

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Jira tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Jira and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { experimental_createMCPClient as createMCPClient } from "@ai-sdk/mcp";

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

if (!process.env.OPENAI_API_KEY) 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,
});

async function main() {
  // Create a tool router session for the user
  const { session } = await composio.create(composioUserID!, {
    toolkits: ["jira"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to jira, like summarize my last 5 emails, send an email, etc... :)))\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({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

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

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Jira agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Jira MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Jira MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Jira MCP with Claude Agent SDK

Google ADK

Google ADK

Use Jira MCP with Google ADK

LangChain

LangChain

Use Jira MCP with LangChain

Mastra AI

Mastra AI

Use Jira MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Jira MCP with LlamaIndex

CrewAI

CrewAI

Use Jira MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Jira MCP?

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

Can I use Tool Router MCP with Vercel AI SDK?

Yes, you can. Vercel AI SDK 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 Jira tools.

Can I manage the permissions and scopes for Jira while using Tool Router?

Yes, absolutely. You can configure which Jira 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.

How safe is my data with Composio Tool Router?

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 Jira data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free