Jira

You can access and manage Jira data through a containerized MCP server that runs Jira-related endpoints. This server lets you query issues, create and update issues, manage comments, and perform project, board, and user operations via a consistent MCP interface, all hosted in a lightweight container. It’s useful when you want to integrate Jira data into your MCP-based workflows and tooling without running Jira directly.

How to use

Run the MCP server and connect to it from your MCP client to perform Jira operations. You can operate in a read-only mode by default, or enable write actions if you understand the implications and want to modify Jira data.

In your MCP client, locate the Jira MCP server you configured and use the available tools to query issues, search by JQL, create or update issues, comment on issues, assign work, transition workflows, manage labels, and retrieve project, board, sprint, and user information. All available endpoints are exposed through the MCP interface as individual tools.

How to install

Prerequisites: ensure you have container tooling and build utilities installed on your system.

Install required utilities and build tools.

Create or obtain a Jira Personal Access Token for authentication and prepare a token file as needed by your deployment.

Configure the MCP server in Cursor by adding a Jira MCP entry with the container command and environment setup described below.

Containerized Jira MCP server configuration

{
  "mcpServers": {
    "jiraMcp": {
      "command": "podman",
      "args": [
        "run",
        "-i",
        "--rm",
        "--env-file",
        "/path/to/your/dotenv/file.env",
        "quay.io/sbaird/jira-mcp:latest"
      ],
      "description": "A containerized MCP server to query Jira issues"
    }
  }
}

Using the HTTP transport (recommended for HTTP-based MCP apps)

If your client communicates over HTTP, start the server with an HTTP transport. First export your environment from the token file, then run the server with the HTTP transport on a port you choose.

export $(grep -v '^#' ~/.rh-jira-mcp.env | xargs) && python server.py --transport http --port 3075

Using the SSE transport (deprecated for new clients)

For older clients that rely on Server-Sent Events (SSE), you can start the server with the SSE transport.

export $(grep -v '^#' ~/.rh-jira-mcp.env | xargs) && python server.py --transport sse --port 3075

Available tools

get_jira

Get details for a specific Jira issue by key.

search_issues

Search issues using JQL.

create_issue

Create a new Jira issue with summary, description, type, priority, and assignee.

update_issue

Update an existing issue's fields such as summary, description, priority, or assignee.

delete_issue

Delete a Jira issue (use with caution).

get_issue_comments

Get all comments for a Jira issue.

add_comment

Add a comment to a Jira issue.

delete_comment

Delete a comment from a Jira issue.

assign_issue

Assign a Jira issue to a user.

unassign_issue

Unassign a Jira issue.

transition_issue

Transition a Jira issue to a new status.

get_issue_transitions

Get available transitions for a Jira issue.

add_issue_labels

Add labels to a Jira issue.

remove_issue_labels

Remove labels from a Jira issue.

list_projects

List all projects.

get_project

Get project details by key.

get_project_components

Get components for a project.

get_project_versions

Get versions for a project.

get_project_roles

Get roles for a project.

get_project_permission_scheme

Get permission scheme for a project.

get_project_issue_types

Get issue types for a project.

list_boards

List all boards.

list_sprints

List sprints for a board.

get_sprint

Get sprint details by ID.

get_sprints_by_name

Get sprints by name for a board.

search_users

Search users by query.

get_user

Get user details by account ID.

get_current_user

Get current user info.

get_assignable_users_for_project

Get assignable users for a project.

get_assignable_users_for_issue

Get assignable users for an issue.