How to integrate Jira MCP with Pydantic AI

This guide walks you through connecting Jira to Pydantic AI 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 through natural language commands. This guide will help you understand how to give your Pydantic AI 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.

Get started for freeGet a demo
Jira logoJira
Oauth2S2s Oauth2Api Key

Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.

94 Tools3 Triggers

Introduction

This guide walks you through connecting Jira to Pydantic AI 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 through natural language commands.

This guide will help you understand how to give your Pydantic AI 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.

Also integrate Jira with

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Jira
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Jira workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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.

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:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

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.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Jira
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Jira
  • MCPServerStreamableHTTP connects to the Jira MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Jira
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["jira"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an 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 session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
jira_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[jira_mcp],
    instructions=(
        "You are a Jira assistant. Use Jira tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Jira endpoint
  • The agent uses GPT-5 to interpret user commands and perform Jira operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Jira.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Jira API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

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

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Jira
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["jira"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    jira_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[jira_mcp],
        instructions=(
            "You are a Jira assistant. Use Jira tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Jira.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Jira through Composio's Tool Router. With this setup, your agent can perform real Jira actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Jira for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS & TRIGGERS

Supported Tools and Triggers

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

Add Attachment

Uploads and attaches a file to a Jira issue.

Add Comment

Adds a comment using Atlassian Document Format (ADF) for rich text to an existing Jira issue.

Add Users to Project Role

Adds users and optionally groups to a project role.

Add User to Group

Adds a user to a Jira group.

Add Watcher to Issue

Adds a user to an issue's watcher list by account ID.

Add Worklog

Tool to add a worklog entry to a Jira issue.

Analyse Jira Expression

Analyses Jira expressions for syntax validation, type checking, and complexity analysis.

Assign Issue

Assigns a Jira issue to a user, default assignee, or unassigns; supports email/name lookup.

Bulk Create Issues

Creates multiple Jira issues (up to 50 per call) with full feature support including markdown, assignee resolution, and priority handling.

Check User Permissions

Check user permissions for global and project-level operations in Jira.

Create Group

Creates a new group in Jira with the specified name.

Create Issue

Creates a new Jira issue (e.

Link Issues

Links two Jira issues using a specified link type with optional comment.

Get JQL Autocomplete Data

Retrieves JQL autocomplete reference data including reserved words, field names, and function names.

Create Project

Creates a new Jira project with required lead, template, and type configuration.

Create Sprint

Creates a new sprint on a Jira board with optional start/end dates and goal.

Create Version

Creates a new version for releases or milestones in a Jira project.

Delete Comment

Deletes 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 Issue

Permanently and irreversibly deletes a Jira issue by its ID or key.

Delete Version

Deletes a Jira version and optionally reassigns its issues.

Delete Worklog

Deletes a worklog from a Jira issue with estimate adjustment options.

Edit Issue

Updates an existing Jira issue with field values and operations.

Evaluate Jira Expression

Tool to evaluate Jira expressions using the enhanced search API.

Bulk Fetch Issues

Tool to bulk fetch multiple Jira issues by their IDs or keys (max 100 per call).

Find Users 2

Tool to find users in Jira by query string, account ID, or property search.

Find Users For Picker

Find users for picker components by matching query against user attributes like display name and email.

Get All Groups

Retrieves all groups from the Jira instance with pagination support.

Get All Issue Type Schemes

Retrieves all Jira issue type schemes with optional filtering and pagination.

Get all projects

Retrieves all visible projects using the modern paginated Jira API with server-side filtering and pagination support.

Get Issue Statuses

Retrieves all issue statuses associated with workflows from Jira.

Get All Users

Retrieves all users from the Jira instance including active, inactive, app accounts, and system accounts, with pagination support.

Get Attachment

Retrieves the binary content of a Jira attachment by ID.

Get Attachment Meta

Tool to retrieve Jira attachment settings including upload limits and enabled status.

Get Comment

Retrieves a specific comment by ID from a Jira issue with optional expansions.

Get Component

Tool to retrieve components from Jira projects with search and filtering.

Get Create Field Metadata for Issue Type

Tool to retrieve field metadata for a specific issue type in a project.

Get Current User

Retrieves detailed information about the currently authenticated Jira user.

Get Dashboards

Tool to list and search Jira dashboards visible to the current user.

Get Favorite Filters

Tool to retrieve favorite filters for the current user.

Get fields

Tool to retrieve Jira issue fields metadata.

Get custom fields paginated

Tool to retrieve Jira fields in pages.

Get Filter

Retrieves a specific Jira saved filter by ID, including its JQL and sharing metadata, to reuse in subsequent searches.

Get Group

Retrieves details of a specific Jira group by name or ID.

Get Service Management Info

Retrieves runtime information for the Jira Service Management instance.

Get Issue

Retrieves a Jira issue by ID or key with customizable fields and expansions.

Get Create Issue Metadata

Tool to retrieve issue creation metadata for Jira projects.

Get Issue Edit Meta

Tool to retrieve editable fields for a Jira issue.

Get Issue Link Types

Retrieves all configured issue link types from Jira.

Get issue picker

Tool to get issue picker suggestions from Jira.

Get Issue Property

Retrieves a custom property from a Jira issue by key.

Get Issue Resolutions

Retrieves all available issue resolution types from Jira.

Get issue types

Retrieves 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 Watchers

Retrieves users watching a Jira issue for update notifications.

Get JQL autocomplete reference data

Tool to retrieve JQL autocomplete reference data.

Get JQL autocomplete suggestions

Tool to get JQL field auto-complete suggestions.

Get My Permissions

Tool to retrieve the user's permissions in Jira.

Get User Locale Preference

Tool to retrieve the locale preference of the currently authenticated Jira user.

Get Permissions

Tool to retrieve all available Jira permissions.

Get Permitted Projects

Tool to retrieve projects where the current user has specific permissions.

Get Project

Retrieves details of a Jira project by its ID or key.

Get Project Roles

Retrieves all available roles for a Jira project.

Get Project Type

Retrieves detailed information about a specific Jira project type by its key.

Get Project Versions

Retrieves all versions for a Jira project with optional expansion.

Get Recent Projects

Retrieves a list of projects recently accessed by the authenticated user.

Get Issue Remote Links

Retrieves links from a Jira issue to external resources.

Get Server Info

Tool to retrieve Jira instance server information.

Get Service Desk Request Type Fields

Tool to retrieve JSM request type field metadata for filling out portal requests.

Get System Avatars

Tool to retrieve all system avatars for a specific type (issuetype, project, user, or priority).

Get Transitions

Retrieves available workflow transitions for a Jira issue.

Get Universal Avatar Type Owner

Tool to retrieve all avatars (system and custom) for a specific type and entity in Jira.

Get Universal Avatar View Type

Tool to retrieve the default avatar image for a specific type (project, issuetype, or priority) from Jira.

Get Avatar Image

Tool to retrieve a specific avatar image by type and ID from Jira.

Get Issue Votes

Fetches voting details for a Jira issue; requires voting to be enabled in Jira's general settings.

Get Worklogs

Retrieves worklogs for a specified Jira issue.

List All Projects

Tool to list all projects accessible to the user.

List Boards

Retrieves paginated Jira boards with filtering and sorting options.

List Comments by IDs

Tool to retrieve multiple comments by their IDs in a single request.

List Jira Filters

Tool to search and list Jira saved filters (saved searches) visible to the current user.

List Groups (Picker)

Tool to search and list groups using Jira's picker endpoint.

List Issue Comments

Retrieves paginated comments from a Jira issue with optional ordering.

List Project Types

Retrieves all Jira project types available in the instance.

List Sprints

Retrieves paginated sprints from a Jira board with optional state filtering.

Move Issues to Sprint

Moves one or more Jira issues to a specified active sprint.

Parse JQL Queries

Parse and validate JQL queries, returning their abstract syntax tree structure along with any errors or warnings.

Remove User from Group

Removes a user from a Jira group.

Remove User from Project Role

Removes a user or group from a project role.

Remove Watcher from Issue

Removes a user from an issue's watcher list by account ID.

Search Approximate Count

Count issues matching a JQL query using approximate count endpoint.

Search Dashboards

Tool to search for Jira dashboards with filtering, sorting, and pagination support.

Search Issues Using JQL (GET)

Searches for Jira issues using JQL with pagination and field selection.

Search issues

Advanced Jira issue search supporting structured filters and raw JQL.

Send Notification for Issue

Sends a customized email notification for a Jira issue.

Transition Issue

Transitions a Jira issue to a different workflow state, with support for transition name lookup and user assignment by email.

Update Comment

Updates text content or visibility of an existing Jira comment.

FRAMEWORKS

How to build Jira MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Jira MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Jira MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Jira MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Jira MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Jira MCP with Claude Cowork

Codex logo

Codex

Use Jira MCP with Codex

Cursor logo

Cursor

Use Jira MCP with Cursor

OpenClaw logo

OpenClaw

Use Jira MCP with OpenClaw

Hermes logo

Hermes

Use Jira MCP with Hermes

CLI logo

CLI

Use Jira MCP with CLI

Google ADK logo

Google ADK

Use Jira MCP with Google ADK

LangChain logo

LangChain

Use Jira MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Jira MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Jira MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Jira MCP with LlamaIndex

CrewAI logo

CrewAI

Use Jira MCP with CrewAI

OpenCode logo

OpenCode

Use Jira MCP with OpenCode

VS Code logo

VS Code

Use Jira MCP with VS Code

FAQ

Frequently asked questions

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.

Yes, you can. Pydantic 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 Jira tools.

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.

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.

Start with Jira.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies