About Jira Cloud
Jira Cloud MCP Server connects MCP clients to Jira Cloud for issue, project, board, sprint, and filter operations. It also provides Jira instance and project data, custom-field catalogs, and tool documentation as resources.
Key features
- 01Create and manage issues
- 02Search with JQL and manage filters
- 03Manage projects, boards, and sprints
- 04Batch operations with result references
- 05Analyze issue metrics and counts
- 06Expose instance and custom-field resources
Use cases
- 01Updating issues and sprint assignments
- 02Running JQL-based issue analysis
- 03Reviewing project and board summaries
- 04Discovering custom fields for issue types
MCP support
It is an MCP server for Jira Cloud. It exposes Jira operations as tools and instance, project, board, custom-field, and documentation data as resources.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @aaronsb/jira-cloud-mcpJIRA_API_TOKENSecretJira API token (generate at https://id.atlassian.com/manage/api-tokens)JIRA_EMAILAtlassian account email addressJIRA_HOSTJira instance URL (e.g., https://your-team.atlassian.net)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
9Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| jql | string | No | JQL query string. Required for create and execute_jql. Read jira://tools/manage_jira_filter/documentation for syntax examples. |
| name | string | No | Filter name. Required for create. |
| expand | array | No | Additional fields to include in the response. |
| startAt | integer | No | Pagination offset (0-based). |
| filterId | string | No | Filter ID. Required for get, update, delete, execute_filter. |
| favourite | boolean | No | Mark as favorite. |
| operation | enum | Yes | Operation to performget | create | update | delete | list | execute_filter | execute_jql |
| maxResults | integer | No | Max items to return. |
| description | string | No | Filter description. |
| sharePermissions | array | No | Share permissions for the filter. |
Details
From the project READMEJira Cloud MCP Server
A Model Context Protocol server for interacting with Jira Cloud instances.
Install
Claude Desktop (one-click)
Download jira-cloud-mcp.mcpb and open it — Claude Desktop will prompt for your Jira credentials.
Claude Code
claude mcp add jira-cloud -e JIRA_API_TOKEN=your-token -e JIRA_EMAIL=your-email -e JIRA_HOST=https://your-team.atlassian.net -- npx -y @aaronsb/jira-cloud-mcp
Manual (any MCP client)
{
"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"
}
}
}
}
Credentials
Generate an API token at Atlassian Account Settings.
Tools
| Tool | Description |
|---|---|
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 |
Each tool accepts an operation parameter (except queue_jira_operations which takes an operations array, and analyze_jira_issues which takes jql + metrics). Per-tool documentation is available as MCP resources at jira://tools/{tool_name}/documentation.
See docs/tools.md for detailed tool descriptions, workspace patterns, and design principles.
MCP Resources
| Resource | Description |
|---|---|
jira://instance/summary | Instance-level statistics |
jira://projects/distribution | Project distribution overview |
jira://projects/{key}/overview | Project overview with status counts |
jira://boards/{id}/overview | Board overview with sprint info |
jira://issue-link-types | Available issue link types |
jira://custom-fields | Custom field catalog (auto-discovered at startup) |
jira://custom-fields/{project}/{issueType} | Context-specific custom fields |
jira://analysis/recipes | Analysis query patterns and compute DSL reference |
jira://tools/{name}/documentation | Per-tool documentation |
License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.