Jira MCP Server

A Model Context Protocol (MCP) server that exposes Jira Cloud to Claude and other LLM agents — enabling programmatic management of Epics, Stories, Tasks, and Sprints directly from an AI chat or agentic workflow.

Stack: Node.js, TypeScript, Fastify, PostgreSQL, Docker, Liquibase

What it does

• Exposes Jira Cloud operations as MCP tools (create/update/query issues, manage sprints, epics)

• Persists conversation context and tool history in PostgreSQL

• Deployable as a Docker container alongside your MCP client

Related MCP server: Jira Cloud MCP Server

Quick start

# 1. Copy env template and fill in your Jira credentials
cp .env.example .env

# 2. Start with Docker Compose (includes Postgres)
docker-compose up

# 3. Run database migrations
docker-compose --profile migrate run --rm liquibase

Configuration

Required env vars (see .env.example):

Development

npm install
npm run start:dev    # watch mode
npm run test         # unit tests
npm run test:e2e     # e2e tests
npm run build        # compile to dist/

MCP client setup

Add to your MCP client config (e.g. Claude Code .mcp.json):

{
  "mcpServers": {
    "jira": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "--env-file", ".env", "jira-mcp"]
    }
  }
}