jira-issue-context-mcp
Read-only MCP server that fetches a single Jira issue by key and returns its title, description, comments, attachment summary, and image attachments.
README
jira-issue-context-mcp
Read-only MCP server that gives Codex, Claude, Cursor, or any MCP client the context for a specific Jira issue.
It intentionally does one thing: fetch a single issue by key and return the issue title, description, comments, attachment summary, and image attachments.
Features
- Single read-only tool:
jira_issue_context - No board listing, sprint browsing, JQL search, transitions, comments, or writes
- Converts Jira ADF descriptions/comments into plain Markdown-ish text
- Paginates all issue comments
- Returns image attachments as MCP
imagecontent - Supports Atlassian Cloud API token auth, bearer auth, or browser/session cookie auth
- Optional Playwright login helper for cookie-based SSO setups
Install
npm install
npm run build
Authentication
Set JIRA_BASE_URL plus one auth method.
You can put these variables in the shell environment or in a .env file in the directory where the MCP command is started. The package also checks its own local .env as a fallback.
Recommended for Atlassian Cloud:
JIRA_BASE_URL=https://your-domain.atlassian.net
JIRA_EMAIL=you@example.com
JIRA_API_TOKEN=your-atlassian-api-token
Bearer token:
JIRA_BASE_URL=https://your-domain.atlassian.net
JIRA_BEARER_TOKEN=your-token
Cookie/session token:
JIRA_BASE_URL=https://your-domain.atlassian.net
JIRA_SESSION_TOKEN=your-cookie-value
JIRA_COOKIE_NAME=tenant.session.token
For SSO environments where API tokens are not available, the login helper can capture a browser cookie:
npx -y --package github:formonkey/jira-issue-context-mcp#main jira-issue-login \
--base-url=https://your-domain.atlassian.net \
--cookie-name=tenant.session.token \
--browser-channel=msedge
Run it from your project root. The login helper writes JIRA_SESSION_TOKEN to .env in the current directory and uses a persistent Playwright profile at .auth/browser-profile by default. --browser-channel=msedge uses your installed Edge instead of downloading Playwright's Chromium. You may need to complete SSO/MFA manually the first time; later runs reuse the browser session while it remains valid.
If Microsoft SSO blocks the automated browser, start Edge yourself with remote debugging and let the helper connect to that real Edge session:
npx -y --package github:formonkey/jira-issue-context-mcp#main jira-issue-login \
--base-url=https://your-domain.atlassian.net \
--cookie-name=tenant.session.token \
--launch-browser=msedge \
--cdp-port=9222 \
--default-profile=true \
--close-existing-browser=true
This closes existing Edge processes, launches a real Edge process with the installed browser's default profile, connects to it over CDP, waits for you to finish Microsoft SSO, captures the Jira session cookie, and writes it to .env.
Advanced manual mode:
start msedge --remote-debugging-port=9222
Then run:
npx -y --package github:formonkey/jira-issue-context-mcp#main jira-issue-login \
--base-url=https://your-domain.atlassian.net \
--cookie-name=tenant.session.token \
--cdp-url=http://127.0.0.1:9222
Both CDP modes are useful for corporate SSO because the browser is launched as a normal installed browser instead of a Playwright-managed browser.
Codex Project Config
Example .codex/config.toml:
[mcp_servers.jira_issue]
command = "node"
args = ["/absolute/path/to/jira-issue-context-mcp/dist/index.js"]
cwd = "/absolute/path/to/jira-issue-context-mcp"
env_vars = [
"JIRA_BASE_URL",
"JIRA_EMAIL",
"JIRA_API_TOKEN",
"JIRA_BEARER_TOKEN",
"JIRA_SESSION_TOKEN",
"JIRA_COOKIE_NAME",
"JIRA_MAX_IMAGE_MB"
]
enabled = true
startup_timeout_sec = 20
tool_timeout_sec = 90
default_tools_approval_mode = "auto"
Then ask your agent:
JIRA CORE-7584: read the issue context and prepare an implementation plan.
The agent should call:
{ "issueKey": "CORE-7584" }
Tool
jira_issue_context
Parameters:
issueKeyrequired in normal chat-driven usage, e.g.CORE-7584includeCommentsoptional, defaults totrueincludeImagesoptional, defaults totruemaxImageSizeMBoptional, defaults toJIRA_MAX_IMAGE_MBor8
The server also supports --issue=KEY or JIRA_ISSUE_KEY as fallback defaults, but passing the issue key from chat is usually cleaner.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。