Jira Cloud MCP Server

MCP server for Jira Cloud — manage issues, sprints, boards, filters, and custom fields

Local serverstdio

What is the Jira Cloud MCP server?

Most planning and project tracking work still happens through a UI a human drives. Jira Cloud MCP server moves it into the conversation instead. MCP server for Jira Cloud — manage issues, sprints, boards, filters, and custom fields.

The short version

A Model Context Protocol server for interacting with Jira Cloud instances.

Getting it running

@aaronsb/jira-cloud-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • manage_jira_issue — Get, create, update, delete, move, transition, comment on, link, or traverse hierarchy of issues
  • manage_jira_filter — Search for issues using JQL queries, or manage saved filters
  • manage_jira_project — List projects or get project configuration and metadata
  • manage_jira_board — List boards or get board details and configuration
  • manage_jira_sprint — Manage sprints: create, start, close, and assign issues to sprints
  • queue_jira_operations — Batch multiple operations with result references ($0.key) and error strategies
  • analyze_jira_issues — Compute metrics, exact counts, and data cube analysis over issues selected by JQL
  • Credentials — Generate an API token at Atlassian Account Settings

What it needs from you

Configuration is passed through the environment: JIRA_API_TOKEN, JIRA_EMAIL, JIRA_HOST. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Jira Cloud's toolset — manage_jira_issue, manage_jira_filter, manage_jira_project and 5 more — is a fair guide to whether it matches your workflow. It is maintained by aaronsb; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
manage_jira_issueGet, create, update, delete, move, transition, comment on, link, or traverse hierarchy of issues
manage_jira_filterSearch for issues using JQL queries, or manage saved filters
manage_jira_projectList projects or get project configuration and metadata
manage_jira_boardList boards or get board details and configuration
manage_jira_sprintManage sprints: create, start, close, and assign issues to sprints
queue_jira_operationsBatch multiple operations with result references ($0.key) and error strategies
analyze_jira_issuesCompute metrics, exact counts, and data cube analysis over issues selected by JQL
CredentialsGenerate an API token at [Atlassian Account Settings](https://id.atlassian.com/manage/api-tokens).

How to install the Jira Cloud MCP server

### Manual (any MCP client)

```json
{
  "mcpServers": {
    "jira-cloud": {
      "command": "npx",
      "args": ["-y", "@aaronsb/jira-cloud-mcp"],
      "env": {
        "JIRA_API_TOKEN": "your-api-token",
        "JIRA_EMAIL": "your-email",
        "JIRA_HOST": "https://your-team.atlassian.net"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
JIRA_API_TOKENCredential the server authenticates with.Yes
JIRA_EMAILConfiguration value read at startup.Optional
JIRA_HOSTEndpoint or connection string the server talks to.Optional

Example prompts to try

  • Use Jira Cloud to manage jira issue.
  • Use Jira Cloud to manage jira filter.
  • Use Jira Cloud to manage jira project.

Frequently asked questions

It connects Jira Cloud to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (manage_jira_issue, manage_jira_filter, manage_jira_project, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Jira Cloud directly.