What dependencies does Jira CLI MCP Server require?
You need jira-cli installed and authenticated. Bun is only needed for development or if building from source.
@choplin
Basic information
MCP server that wraps jira-cli to enable AI assistants to interact with Jira
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"jira-cli-mcp": {
"command": "bun",
"args": [
"run",
"build:prod"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol server that wraps the jira-cli command-line tool to enable AI assistants to interact with Jira. It leverages existing jira-cli setup and authentication, requiring no API tokens in config files and no Docker containers.
Install and configure jira-cli first, then install jira-cli-mcp via Homebrew, npm, or pre-compiled binary. Add the server to your AI assistant’s MCP configuration (e.g., Claude Desktop claude_desktop_config.json or Claude Code .claude/mcp.json) and restart the assistant.
You need jira-cli installed and authenticated. Bun is only needed for development or if building from source.
Authentication is handled entirely by jira-cli, not by the server itself. No API tokens are stored in config files.
Claude Desktop, Claude Code, and GitHub Copilot (VS Code version 1.99+ in public preview) are supported with MCP configuration files.
The server uses Atlassian Document Format for rich text; Markdown input is automatically converted to ADF by jira-cli.
Yes, set the `JIRA_CLI_PATH` environment variable to specify a custom path (default is "jira").
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Comments