About Jira MCP Server
Jira MCP Server is a simple server for AI assistants to perform selected Jira ticket actions. Docker-based deployment is provided, and it can also be run with Python.
Key features
- 01Fetch assigned tickets
- 02Add comments to tickets
- 03Retrieve available status transitions
- 04Update ticket status
- 05Docker-based deployment
Use cases
- 01Review tickets assigned to a Jira user
- 02Add a comment to a ticket
- 03Check available status transitions
- 04Change a ticket's status
MCP support
Exposes Jira ticket actions to MCP clients at the `/mcp` endpoint, including fetching assigned tickets, comments, and status updates.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEJira MCP Server
A Simple Model Context Protocol (MCP) server that allows AI assistants to interact with Jira. This server enables AI to perform actions like:
- Fetching user's assigned tickets
- Adding comments to tickets
- Getting available status transitions
- Updating ticket status
Prerequisites
- Docker
- Jira account with API access
- Environment variables configured (see below)
Environment Variables
Create a .env file in the root directory with the following:
JIRA_SERVER=https://yourcompany.atlassian.net
[email protected]
JIRA_API_KEY=yourapikey
JIRA_PROJECT_KEY=yourprojectkey
Get your API key from: https://id.atlassian.com/manage-profile/security/api-tokens
Running Locally
Option 1: Using Docker
# Build and run with Docker
chmod +x run_docker_locally.sh
./run_docker_locally.sh
Option 2: Using Python
- Install dependencies:
pip install -r requirements.txt
- Run the server:
uvicorn src.server:app --reload
This will start the server on http://localhost:8000.
Using the MCP Server
The MCP server is exposed at http://localhost:8000/mcp.
Comments
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.