playbooks
Learn Cursor Rules Windsurf Rules MCPs Modes
Log in

JIRA Snowflake MCP server

Provides access to JIRA issue data exported from Snowflake as CSV files, enabling querying, filtering, and analysis of issues with project statistics and detailed metadata without requiring direct JIRA API access.
Back to servers
Setup instructions
Provider
rshemtov13
Release date
May 29, 2025
Language
TypeScript
View on GitHub

The Jira MCP Server is a specialized tool that provides AI assistants with access to JIRA issue data stored in Snowflake. This server exposes a standardized interface through the Model Context Protocol, allowing for querying, filtering, and analyzing JIRA issues without direct access to the JIRA platform.

Installation

Prerequisites

  • Python 3.8 or higher
  • Podman or Docker
  • Access to Snowflake with appropriate credentials

Container Deployment

Building the Container

To build the container image locally using Podman:

podman build -t jira-mcp-snowflake:latest .

Running with Podman or Docker

Create a configuration with appropriate environment variables:

podman run -i --rm \
  -e SNOWFLAKE_TOKEN=your_token_here \
  -e SNOWFLAKE_BASE_URL=https://your-account.snowflakecomputing.com/api/v2 \
  -e SNOWFLAKE_DATABASE=your_database_name \
  -e SNOWFLAKE_SCHEMA=your_schema_name \
  -e MCP_TRANSPORT=stdio \
  -e ENABLE_METRICS=true \
  -e METRICS_PORT=8000 \
  localhost/jira-mcp-snowflake:latest

Local Development Setup

  1. Clone the repository:
git clone <repository-url>
cd jira-mcp-snowflake
  1. Install dependencies:
pip install -r requirements.txt
  1. Set the required environment variables:
export SNOWFLAKE_TOKEN=your_token_here
export SNOWFLAKE_BASE_URL=https://your-account.snowflakecomputing.com/api/v2
export SNOWFLAKE_DATABASE=your_database_name
export SNOWFLAKE_SCHEMA=your_schema_name
  1. Run the server:
python src/mcp_server.py

Configuration

Required Environment Variables

  • SNOWFLAKE_TOKEN - Your Snowflake authentication token
  • SNOWFLAKE_BASE_URL - Snowflake API base URL
  • SNOWFLAKE_DATABASE - Snowflake database containing JIRA data
  • SNOWFLAKE_SCHEMA - Snowflake schema containing JIRA tables

Optional Environment Variables

  • MCP_TRANSPORT - Protocol for MCP communication (default: stdio)
  • ENABLE_METRICS - Enable Prometheus metrics (default: false)
  • METRICS_PORT - Port for metrics HTTP server (default: 8000)

Integration with VS Code Continue

Add this configuration to integrate with VS Code Continue:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "name": "jira-mcp-snowflake",
        "transport": {
          "type": "stdio",
          "command": "podman",
          "args": [
            "run",
            "-i",
            "--rm",
            "-e", "SNOWFLAKE_TOKEN=your_token_here",
            "-e", "SNOWFLAKE_BASE_URL=https://your-account.snowflakecomputing.com/api/v2",
            "-e", "SNOWFLAKE_DATABASE=your_database_name",
            "-e", "SNOWFLAKE_SCHEMA=your_schema_name",
            "-e", "MCP_TRANSPORT=stdio",
            "-e", "ENABLE_METRICS=true",
            "-e", "METRICS_PORT=8000",
            "localhost/jira-mcp-snowflake:latest"
          ]
        }
      }
    ]
  }
}

Available Tools

List Issues (list_issues)

Query and filter JIRA issues with various criteria:

# List all issues from the SMQE project
result = await list_issues(project="SMQE", limit=10)

# Search for issues containing "authentication"
result = await list_issues(search_text="authentication", limit=20)

Parameters:

  • project - Filter by project key (e.g., 'SMQE', 'OSIM')
  • issue_type - Filter by issue type ID
  • status - Filter by issue status ID
  • priority - Filter by priority ID
  • search_text - Search in summary and description fields
  • limit - Control number of results returned (default: 50)

Get Issue Details (get_issue_details)

Retrieve comprehensive information for a specific JIRA issue:

# Get detailed information for a specific issue
result = await get_issue_details(issue_key="SMQE-1280")

Parameters:

  • issue_key - The JIRA issue key (e.g., 'SMQE-1280')

Get Project Summary (get_project_summary)

Generate statistics across all projects:

# Get statistics for all projects
result = await get_project_summary()

Monitoring

When metrics are enabled, the server provides monitoring endpoints:

  • /metrics - Prometheus metrics endpoint for scraping
  • /health - Health check endpoint returning JSON status

The metrics include:

  • Tool usage tracking
  • Snowflake query performance
  • Active MCP connections

Access metrics at: http://localhost:8000/metrics

Security Considerations

  • Store sensitive information like SNOWFLAKE_TOKEN in environment variables
  • Ensure your Snowflake token is kept secure and rotated regularly
  • Use HTTPS endpoints and secure network connections
  • Follow principle of least privilege for Snowflake database access

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "jira-mcp-snowflake" '{"command":"podman","args":["run","-i","--rm","-e","SNOWFLAKE_TOKEN=your_token_here","-e","SNOWFLAKE_BASE_URL=https://your-account.snowflakecomputing.com/api/v2","-e","SNOWFLAKE_DATABASE=your_database_name","-e","SNOWFLAKE_SCHEMA=your_schema_name","-e","MCP_TRANSPORT=stdio","-e","ENABLE_METRICS=true","-e","METRICS_PORT=8000","localhost/jira-mcp-snowflake:latest"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "jira-mcp-snowflake": {
            "command": "podman",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "SNOWFLAKE_TOKEN=your_token_here",
                "-e",
                "SNOWFLAKE_BASE_URL=https://your-account.snowflakecomputing.com/api/v2",
                "-e",
                "SNOWFLAKE_DATABASE=your_database_name",
                "-e",
                "SNOWFLAKE_SCHEMA=your_schema_name",
                "-e",
                "MCP_TRANSPORT=stdio",
                "-e",
                "ENABLE_METRICS=true",
                "-e",
                "METRICS_PORT=8000",
                "localhost/jira-mcp-snowflake:latest"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "jira-mcp-snowflake": {
            "command": "podman",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "SNOWFLAKE_TOKEN=your_token_here",
                "-e",
                "SNOWFLAKE_BASE_URL=https://your-account.snowflakecomputing.com/api/v2",
                "-e",
                "SNOWFLAKE_DATABASE=your_database_name",
                "-e",
                "SNOWFLAKE_SCHEMA=your_schema_name",
                "-e",
                "MCP_TRANSPORT=stdio",
                "-e",
                "ENABLE_METRICS=true",
                "-e",
                "METRICS_PORT=8000",
                "localhost/jira-mcp-snowflake:latest"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later