Get Issue By KeyLABSCO SUMMARY
Triage without the browser tab.
The set of operations lines up with what people do in Jira all day rather than with the API surface: find it, assign it, move it, close it. Two things to know before you commit: the author flags the project as a work in progress, and only Jira Cloud endpoints have been tested — the Data Center path may work but has not been verified, so point it at a Cloud site if you have the choice.
What it is
A Node MCP server that talks to Jira's REST API using your account's API key, exposing the issue operations a day of triage actually needs.
What you get
- Get Issue By Key and Search Issues, for finding the ticket you mean
- Create Issue, against a default project key you set once
- Assign Issue and Unassign Issue
- Edit Issue and Transition Issue, for moving work along without opening Jira
- Archive Issues, for clearing out what is finished
Requirements
Clone, npm install, npm run build. Four environment variables in the client: JIRA_PROJECT_URL ending in /rest/api/3, JIRA_USER_EMAIL (the API needs it for authorization), JIRA_API_KEY, and JIRA_PROJECT_KEY as the default for new issues.
Setup effort
Build from source — git clone https://github.com/brianstone/jira-mcp-server.git
USE CASES
Clearing a triage queue
Search for the unassigned issues in the project and assign each to the right person from the conversation.
Filing a bug as you find it
Create the issue against the default project key without breaking out of what you were doing.
Moving a ticket to done
Look the issue up by key and transition it, rather than clicking through the board.
8 tools
Listed in project docs. Your client may show a different list.
Search IssuesCreate IssueAssign IssueUnassign IssueEdit IssueTransition IssueArchive IssuesBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
- node on PATH
- JIRA_PROJECT_URL in your environment
- JIRA_USER_EMAIL in your environment
- JIRA_API_KEY in your environment
- JIRA_PROJECT_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
git clone https://github.com/brianstone/jira-mcp-server.git
cd jira-mcp-server
npm install
npm run buildMCP Clients
Claude Desktop, Cursor
{
"mcpServers": {
"jira-mcp-server": {
"command": "node",
"args": [
"<YOUR_PATH_TO_REPO>/jira-mcp-server/build/index.js"
],
"env": {
"JIRA_PROJECT_URL": "https://project-url.atlassian.net/rest/api/3",
"JIRA_USER_EMAIL": "<YOUR_JIRA_USER_EMAIL>",
"JIRA_API_KEY": "<YOUR_JIRA_API_KEY>",
"JIRA_PROJECT_KEY": "ABC"
}
}
}
}<YOUR_PATH_TO_REPO>/jira-mcp-server/build/index.js is the full path of build/index.js in your clone (npm run build creates it). A relative path resolves from wherever the client starts. Set JIRA_PROJECT_URL to your site's REST base ending in /rest/api/3 (like https://your-project.atlassian.net/rest/api/3), JIRA_USER_EMAIL to your Atlassian account email, JIRA_API_KEY to an Atlassian API token, and JIRA_PROJECT_KEY to the project new issues go into.