jira-mcp-ai

jira-mcp-ai is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from IvanBBaev/jira-mcp. Its token cost is not measured, scanned A, original, MIT.

A local MCP server for Jira Cloud, an online system for tracking tasks and software issues. It supports searches, issue reads, comments, worklogs, boards, sprints, and controlled writes using API-token authentication.

In plain words
What is it for?
Finding and reading Jira issues, adding comments or worklogs, working with boards and sprints, and applying planned Jira changes.
Why use it?
It lets an agent work with Jira from local tools while staying read-only by default and requiring a plan before changes. It also includes settings for access, limits, retries, and transport.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

Good fit Finding and reading Jira issues, adding comments or worklogs, working with boards and sprints, and applying planned Jira changes.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/ivanbbaev/jira-mcp/jira-mcp-ai
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/IvanBBaev/jira-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for jira-mcp-ai

README.md
[![agentmods](https://agentmods.dev/badge/mcp/ivanbbaev/jira-mcp/jira-mcp-ai/github.svg)](https://agentmods.dev/mcp/ivanbbaev/jira-mcp/jira-mcp-ai)
Your own site
<a href="https://agentmods.dev/mcp/ivanbbaev/jira-mcp/jira-mcp-ai"><img src="https://agentmods.dev/badge/mcp/ivanbbaev/jira-mcp/jira-mcp-ai/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for jira-mcp-ai

Your own site · 80×15
<a href="https://agentmods.dev/mcp/ivanbbaev/jira-mcp/jira-mcp-ai"><img src="https://agentmods.dev/badge/mcp/ivanbbaev/jira-mcp/jira-mcp-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

jira-mcp-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 45 lines

What it actually says

{
  "jira-mcp-ai": {
    "command": "npx",
    "args": [
      "-y",
      "jira-mcp-ai"
    ],
    "env": {
      "JIRA_SITE": "",
      "JIRA_EMAIL": "",
      "JIRA_API_TOKEN": "",
      "JIRA_ENV_FILE": "",
      "JIRA_TOKEN_EXPIRES": "",
      "JIRA_ALLOWED_HOSTS": "",
      "JIRA_ACTIVE_PROFILE": "",
      "JIRA_LOCK_PROFILE": "true",
      "JIRA_TOOL_PACKAGES": "all",
      "JIRA_PACKAGES_DENY": "",
      "JIRA_PACKAGES_READONLY": "",
      "JIRA_WRITE_MODE": "plan",
      "JIRA_ALLOW_IRREVERSIBLE": "false",
      "JIRA_REQUEST_TIMEOUT_MS": "30000",
      "JIRA_CALL_BUDGET_MS": "120000",
      "JIRA_HOST_CONCURRENCY": "4",
      "JIRA_RETRY_ATTEMPTS": "3",
      "JIRA_MAX_RESULT_CHARS": "25000",
      "JIRA_MAX_PAGES": "20",
      "JIRA_MEDIA_DIR": "",
      "JIRA_TRANSPORT": "stdio",
      "JIRA_HTTP_PORT": "3334",
      "JIRA_HTTP_TOKEN": "",
      "JIRA_LOG_LEVEL": "info",
      "JIRA_JOURNAL_PATH": "",
      "JIRA_AUTH_MODE": "basic",
      "JIRA_OAUTH_CLIENT_ID": "",
      "JIRA_OAUTH_CLIENT_SECRET": "",
      "JIRA_OAUTH_SCOPES": "read:jira-work,write:jira-work,read:jira-user,manage:jira-project,read:board-scope:jira-software,write:board-scope:jira-software,read:sprint:jira-software,write:sprint:jira-software,read:epic:jira-software,write:epic:jira-software,read:issue:jira-software,write:issue:jira-software,offline_access",
      "JIRA_OAUTH_CLOUD_ID": "",
      "JIRA_OAUTH_TOKEN_FILE": "<config dir>/oauth.json",
      "JIRA_OAUTH_REDIRECT_PORT": "8250",
      "JIRA_OAUTH_AUTH_ORIGIN": "https://auth.atlassian.com",
      "JIRA_OAUTH_GATEWAY_ORIGIN": "https://api.atlassian.com"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 45 lines scan A abfb1aaafe94

Subscribe to this mod's changes

jira-mcp-ai is an MCP server published in the GitHub repository IvanBBaev/jira-mcp (0 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other mcp servers, from other repositories

atlassian-mcp-server

MCP server for Atlassian APIs (Jira, Confluence, Bitbucket). Runs locally from the @jagadeesh52423/atlassian-mcp-server npm package.

jagadeesh52423/ConfluenceMcp · not measured

jira-admin-mcp

A Model Context Protocol (MCP) server giving AI assistants 78 tools to administer a Jira Cloud site: issues, users, groups, projects, permissions, custom fields, workflows, screens, filters, and bulk operations. Runs locally from the jira-admin-mcp Python package. Needs 4 environment variables to run.

its-qusai-nasr/jira-admin-mcp · not measured

atlassian-mcp

MCP server for Jira & Confluence — 53 tools for issue management, sprint planning, board management, and Confluence page management. Runs locally from the atlassian-mcp Python package.

halim-23/jira-mcp-server · not measured

jira-server

Enterprise-grade Model Context Protocol server for comprehensive Jira integration with automated field detection, multi-instance support, and cross-server capabilities. Runs locally from the jira-server npm package.

cfdude/mcp-jira · not measured

jira-mcp-server

MCP server for Jira — search, create, update, transition issues, manage projects, boards, and spr... Runs locally from the @supernova123/jira-mcp-server npm package.

friendlygeorge/jira-mcp-server · not measured

mcp-atlassian-extended

Extended MCP tools for Jira and Confluence — attachments, agile boards, sprints, calendars. Runs locally from the mcp-atlassian-extended Python package. Needs 5 environment variables to run.

vish288/mcp-atlassian-extended · not measured