What runtime does Jira Pilot require?
Node.js 20.0.0 or higher is required.

@Aarul5
AI-powered Jira CLI and MCP server for humans and agents manage issues, sprints, boards with interactive wizards, multi-provider AI (OpenAI/Gemini/Anthropic), and an 14-tool MCP server for AI assistants
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"jira-pilot": {
"command": "npx",
"args": [
"-y",
"jira-pilot@latest",
"mcp"
],
"env": {
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "<YOUR_API_TOKEN>"
}
}
}
}List Jira issues using JQL. Returns key, summary, status, and assignee for each issue.
Get full details of a specific Jira issue including summary, description, status, assignee, priority, and comments.
Create a new Jira issue in a project. Returns the created issue key.
Update an existing Jira issue. Supports updating summary, description, priority, and assignee.
Transition a Jira issue to a new status. First call with only issueKey to see available transitions, then call again with the transitionId.
Assign or unassign a Jira issue. Use accountId to assign, or null to unassign.
Add a comment to a Jira issue.
Search for Jira users by name or email. Returns accountId and displayName.
Get details about the current authenticated user.
List all accessible Jira projects. Returns project key, name, lead, and style.
List sprints for a Jira board. Requires a board ID.
Log work to a Jira issue.
Create a subtask for a parent issue.
Attach a file to a Jira issue.
Jira Pilot is an AI-powered CLI and Model Context Protocol (MCP) server for Jira. It provides an interactive command-line interface for humans to manage issues, sprints, boards, and code, and a fully compliant MCP server with 14 tools that lets AI assistants interact with your Jira instance.
Install globally with npm install -g jira-pilot, then run jira config setup to configure credentials, site URL, and optional AI provider. Use the jira command for interactive CLI workflows or connect the MCP server via stdio transport to any MCP client like Claude Desktop.
Node.js 20.0.0 or higher is required.
Run `jira config setup` and provide your Jira site URL, email, API token, and optionally enable AI with a provider (OpenAI, Gemini, Anthropic) and API key.
The MCP server uses stdio transport, compatible with any MCP client.
Yes, you can save multiple credential profiles (e.g., work, personal) and switch between them with `jira config use <profile>`.
The MCP tools require a running Jira instance accessible via API. Bulk operations ask for confirmation before applying changes. AI features require an API key for the chosen provider.
MCP server for Atlassian tools (Confluence, Jira)
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed).
A Model Context Protocol (MCP) server that helps read GitHub repository structure and important files.
A Go-based MCP (Model Control Protocol) connector for Jira that enables AI assistants like Claude to interact with Atlassian Jira. This tool provides a seamless interface for AI models to perform common Jira operations including issue management, sprint planning, and workflow tra
MCP server connecting AI assistants with Jira & Confluence for smart project management.
评论