mcpField
J
Jira Prompts MCP Server

Jira Prompts MCP Server

Local
github.com/ceshineVersion Control0Updated 75w ago

About Jira Prompts MCP Server

Jira Prompts MCP Server generates prompts and context from Jira issues, for users of MCP clients that support prompts. It offers brief and full issue views, with the full view including comments, linked issues, and subtasks.

Key features

  1. 01Generate a brief Jira issue prompt
  2. 02Generate a full issue prompt with related context
  3. 03Retrieve issue data by Jira key
  4. 04Include comments, linked issues, and subtasks

Use cases

  1. 01Get a concise brief for a Jira issue
  2. 02Prepare full issue context for an assistant
  3. 03Use Jira prompts in clients that support MCP prompts

MCP support

Provides MCP prompts for Jira issues rather than tools. The `jira-issue-brief` and `jira-issue-full` prompts retrieve issue information by issue key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Jira Prompts MCP Server

This repository provides a Model Context Protocol (MCP) server that offers several commands for generating prompts or contexts from Jira content.

This repository draws significant inspiration from the MarkItDown MCP server and the example Git MCP server. It also incorporates design and code elements from the mcp-atlassian repository. The main differences between this repository and mcp-atlassian are that it uses pycontribs/jira instead of atlassian-api/atlassian-python-api to interact with the Jira API, and it focuses on providing prompts rather than tools. The latter makes it especially useful when working with tools that support only MCP prompts, such as Zed's AI assistant.

Here's another MCP server project of mine: ceshine/git-prompts-mcp-server

Changelog

0.1.0
  • Migrate from the low-level mcp package to the FastMCP package.
  • Add a CLI for testing the server.
0.0.1

The initial release with two prompts implemented: jira-issue-brief and jira-issue-full.

Installation

Manual Installation
  1. Clone this repository
  2. Install dependencies: uv sync --frozen

Usage

As a MCP Server for Zed Editor

Add the following to your settings.json:

"context_servers": {
  "git_prompt_mcp": {
    "command": {
      "path": "uv",
      "args": [
        "--directory",
        "/path/to/local/jira_prompts_mcp_server",
        "run",
        "jira-prompts-mcp-server",
        "https://my-company.atlassian.net", // Jira base URL
        "[email protected]",  // Jira username
        "your_api_key"  // Jira API token (https://id.atlassian.com/manage-profile/security/api-tokens)
      ]
    },
    "settings": {}
  }
}
Commands

The server responds to the following commands:

  1. jira-issue-brief <issue-key>: Retrieves the core fields of a Jira issue. Requires the issue key (e.g., PROJ-123) as an argument.
  2. jira-issue-full <issue-key>: Retrieves the core fields, comments, linked issues, and subtasks of a Jira issue. Requires the issue key as an argument.

Examples:

  1. /jira-issue-brief PROJ-123
  2. /jira-issue-brief PROJ-155
Testing the server using the CLI

Prerequisities: configuring the required environment variables (JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN)

You can quickly test the MCP server using the CLI. Below are some example commands:

  • uv run python -m jira_prompts_mcp_server.cli jira-brief BOOM-1234
  • uv run python -m jira_prompts_mcp_server.cli jira-full BOOM-1234

License

MIT License. See LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.