Jira MCP Server
A Jira integration server that provides tools for fetching ticket details and searching tickets using the MCP (Model Control Protocol) framework.
Setup
- Install the required dependencies: For local env use:
./setup.sh
Alternatively
pip install -r requirements.txt
- Create a
.envfile in the project root with your Jira credentials:
JIRA_URL=https://your-domain.atlassian.net
[email protected]
JIRA_API_TOKEN=your-api-token
Running the Application
The server can be run in two modes:
- Standard I/O Mode (default):
python main.py
- SSE Mode for Cursor:
./run.sh --transport sse --port 8000
OR
python main.py --transport sse --port 8000
Once the server has started Go to Cursor Settings > MCP > Add new Global MCP Server
Paste the following in the JSON
{
"mcpServers": {
"jira": {
"url": "http://localhost:8000/sse",
"env": {
"JIRA_URL": "YOUR_JIRA_URL",
"JIRA_USERNAME": "YOUR_JIRA_USERNAME",
"JIRA_API_TOKEN": "YOUR_JIRA_API_TOKEN"
}
}
}
}
Available Tools
1. Fetch Ticket Details
Fetches detailed information about a Jira ticket.
Input Schema:
{
"ticketKey": "string", // Required: Jira ticket key (e.g., PROJ-123)
"includeComments": "boolean", // Optional: Whether to include comments, default true
"includeAttachments": "boolean" // Optional: Whether to include attachments, default true
}
Response: Returns a JSON object containing:
- Basic ticket information (key, summary, description, status, etc.)
- Custom fields
- Comments (if requested)
- Attachments (if requested)
2. Search Tickets
Searches for Jira tickets using JQL (Jira Query Language).
Input Schema:
{
"jql": "string", // Required: JQL query string
"maxResults": "integer" // Optional: Maximum number of results (default: 50)
}
Response: Returns an array of ticket summaries containing:
- Ticket key
- Summary
- Status
- Assignee
- Priority
Features
- Comprehensive Jira ticket data retrieval
- Support for custom fields
- JQL-based ticket searching
- Optional inclusion of comments and attachments
- Error handling and validation
- Multiple transport options (stdio/SSE)
Recommend MCP Servers 💡
@jetbrains/mcp-proxy
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
lean-docker-mcp
A Dockerized Lean4 execution environment MCP server for AI agents, providing isolated code execution with transient or persistent environments.
@inhiblab-core/mcp-image-compression
A high-performance image compression microservice based on MCP (Modal Context Protocol)
mcp-language-server
An MCP server that runs and exposes a language server to LLMs, providing semantic tools like get definition, references, rename, and diagnostics to MCP enabled clients.
npm-search-mcp-server
A Model Context Protocol server that allows you to search for npm packages by calling the `npm search` command