JIRA MCP Server
Enables interaction with JIRA through the MCP interface, allowing users to manage issues, sprints, and users via natural language commands.
README
JIRA MCP Server
This is a Model Context Protocol (MCP) server that provides tools for interacting with JIRA. It allows you to fetch tickets from active sprints, search issues, manage users, and get detailed ticket information through the MCP interface.
⚠️ Updated for 2025: This fork includes critical fixes for Atlassian's API deprecations that caused 410 errors in the original version. All deprecated endpoints have been replaced with their modern equivalents.
Features
The server provides the following tools:
Issue Management
-
search-issues: Search for issues using JQL or filters- Optional parameter:
jql(string) - Custom JQL query - Optional parameter:
projectKey(string) - Filter by project - Optional parameter:
issueType(string) - Filter by issue type (e.g., 'Bug', 'Task', 'Story') - Optional parameter:
statusCategory(string) - Filter by status ('To Do', 'In Progress', 'Done') - Optional parameter:
maxResults(number) - Max results to return (default: 20, max: 100) - Optional parameter:
startAt(number) - Pagination offset
- Optional parameter:
-
list-sprint-tickets: Gets all tickets in the active sprint for a given project- Required parameter:
projectKey(string)
- Required parameter:
-
get-ticket-details: Gets detailed information about a specific ticket- Required parameter:
issueKey(string)
- Required parameter:
-
add-comment: Adds a comment to a specific ticket- Required parameter:
issueKey(string) - Required parameter:
comment(string)
- Required parameter:
-
update-description: Updates the description of a specific ticket- Required parameter:
issueKey(string) - Required parameter:
description(string)
- Required parameter:
-
list-child-issues: Gets all child issues of a parent ticket- Required parameter:
parentKey(string)
- Required parameter:
-
create-sub-ticket: Creates a sub-ticket (child issue) for a parent ticket- Required parameter:
parentKey(string) - Required parameter:
summary(string) - Optional parameter:
description(string) - Optional parameter:
issueType(string) - The name of the sub-task issue type (e.g., 'Sub-task')
- Required parameter:
-
create-ticket: Create a new ticket with custom fields- Required parameter:
projectKey(string) - Required parameter:
summary(string) - Optional parameter:
description(string) - Optional parameter:
issueType(string) - Optional parameter:
parentKey(string) - Creates a sub-task if provided - Optional parameter:
fields(object) - Additional custom fields
- Required parameter:
-
update-issues: Batch update fields on multiple tickets- Required parameter:
issueKeys(array of strings) - Required parameter:
fields(object) - Fields to update
- Required parameter:
-
add-labels: Add labels to multiple issues- Required parameter:
issueKeys(array of strings) - Required parameter:
labels(array of strings)
- Required parameter:
-
link-issues: Link multiple tickets using 'relates to' relationship- Required parameter:
inwardIssueKeys(array of strings) - Required parameter:
outwardIssueKeys(array of strings)
- Required parameter:
-
transition-issues: Transition multiple issues to a new status- Required parameter:
issueKeys(array of strings) - Required parameter:
transitionId(string)
- Required parameter:
-
list-issue-transitions: List available transitions for an issue- Required parameter:
issueKey(string)
- Required parameter:
-
assign-issue: Assign issues to a user- Required parameter:
issueKeys(array of strings) - Required parameter:
assigneeDisplayName(string)
- Required parameter:
User & Field Management
-
list-users: List all users in Jira- Optional parameter:
query(string) - Search string to filter users - Optional parameter:
maxResults(number) - Max results (default: 50, max: 1000)
- Optional parameter:
-
list-issue-fields: List all available issue fields including custom fields- Optional parameter:
includeCustomOnly(boolean) - Only show custom fields
- Optional parameter:
-
list-jira-filters: List all Jira filters
Setup
-
Install dependencies:
npm install -
Build the TypeScript code:
This step is only needed for Cline on Windows, which currently has an issue executing npx
npm run build
- Configure the MCP settings in your Claude app settings file (usually located at
~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS or%APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.jsonon Windows):
Settings for Claude:
{
"mcpServers": {
"jira": {
"command": "npx",
"args": ["path/to/this/repo/jira.ts"],
"env": {
"JIRA_HOST": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Settings for Cline:
{
"mcpServers": {
"jira": {
"command": "node",
"args": ["path/to/this/repo/dist/jira.js"],
"env": {
"JIRA_HOST": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Configuration
Option 1: Local Development with .env file
For local development and testing, you can use a .env file:
-
Copy the example file:
cp .env.example .env -
Edit
.envand add your credentials:JIRA_HOST=https://your-domain.atlassian.net JIRA_EMAIL=your-email@example.com JIRA_API_TOKEN=your-api-token -
Run the server:
npm start
Option 2: MCP Configuration
You'll need to set up the following environment variables in your MCP settings:
JIRA_HOST: Your Atlassian domain URL (e.g.,https://your-company.atlassian.net)JIRA_EMAIL: Your JIRA account emailJIRA_API_TOKEN: Your JIRA API token- You can generate an API token from your Atlassian Account Settings
Usage
Once configured, you can use the tools through the MCP interface in Claude:
List Sprint Tickets
To get all tickets in the active sprint for a project:
<use_mcp_tool>
<server_name>jira</server_name>
<tool_name>list-sprint-tickets</tool_name>
<arguments>
{
"projectKey": "YOUR_PROJECT_KEY"
}
</arguments>
</use_mcp_tool>
Get Ticket Details
To get detailed information about a specific ticket:
<use_mcp_tool>
<server_name>jira</server_name>
<tool_name>get-ticket-details</tool_name>
<arguments>
{
"issueKey": "PROJECT-123"
}
</arguments>
</use_mcp_tool>
Development
The server is written in TypeScript and uses:
@modelcontextprotocol/sdkfor MCP server implementationjira.jsfor JIRA API integration
Recommended scripts:
- Build once:
npm run build - Build and watch:
npm run build:watch - Type-check only:
npm run typecheck - Dev run with watch:
npm run start:dev - Run compiled server:
npm start - Format check:
npm run fmt:check - Format write:
npm run fmt
Typical workflow:
- Make changes to
jira.ts - Run
npm run start:devduring development, ornpm run buildthennpm startfor compiled run - Restart your MCP client if needed to pick up changes
Recent Updates (2025)
Critical Fixes for Atlassian API Deprecations
This fork includes fixes for the following deprecated endpoints that were causing 410 Gone errors:
-
/rest/api/3/users/search→ Migrated to/rest/api/3/user/search- Affects:
list-userstool - Fixed: Updated to use
userSearch.findUsers()with proper pagination
- Affects:
-
/rest/api/3/search→ Migrated to/rest/api/3/search/jql- Affects:
search-issuesandlist-sprint-ticketstools - Fixed: Updated to use
searchForIssuesUsingJqlEnhancedSearch()with token-based pagination - Note: The new API requires bounded JQL queries (unbounded queries now default to last 30 days)
- Affects:
Other Improvements
- Updated
jira.jsdependency from 4.1.3 to 5.2.2 - Added
.envfile support for local development withdotenv - Enhanced error messages with full response details for easier debugging
- Added test script (
test-local.sh) for local development - Improved pagination handling with new token-based system
Error Handling
The server includes error handling for:
- Invalid JIRA credentials
- Missing active sprints
- Invalid project keys or issue keys
- Network errors
- Deprecated API endpoints (with automatic migration to new endpoints)
Error messages will be returned in the tool response with detailed information.
Migration from Original Version
If you're migrating from the original boukeversteegh/mcp-server-jira:
-
Update your local repository:
git pull npm install npm run build -
Restart your MCP client (Cursor/Claude)
-
All tools should now work without 410 errors
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
Apache-2.0 License
Credits
- Original version by boukeversteegh
- 2025 updates and fixes by aderik
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.