Jira MCP Server Af59130e

MCPAI代理

提供方 coollikeabreeze

AI代理 未标注 Token 社区 / 第三方

一个实现MCP协议和REST API的服务器,用于创建Jira问题,支持MCP兼容客户端和ChatGPT自定义GPT动作集成。

一句话选型结论

按资料字段整理

Jira MCP Server Af59130e 属于AI代理类 MCP 服务器,传输方式未标注,Token,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式未标注 鉴权Token 部署方式未标注
GitHub 星标 0 仓库热度,无公开仓库时显示未标注
工具数 1 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量1暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

适用场景

Jira集成TypeScript本地部署MCP协议RESTAPI问题管理自动化工具

安装与配置

未标注 Token
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 1 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 1 个工具,职责相对集中,接入后不容易误操作。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好Token对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Jira MCP Server Af59130e当前 1 未标注 未标注 无 2026-05-17
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方coollikeabreeze上游标注的维护方 coollikeabreeze
分类AI代理本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式Token远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

9.4 KB
来自项目仓库与上游目录的原文,未做删改

Jira MCP Server

A Model Context Protocol (MCP) server for creating Jira issues. This server implements the MCP protocol and can be used with MCP-compatible clients (like Postman MCP Client) or integrated as a Custom GPT Action for ChatGPT.

Overview

This is a dual-purpose server that provides:

  • MCP Protocol Endpoint (/mcp) - For MCP-compatible clients using the Model Context Protocol
  • REST API Endpoint (/api/create-issue) - For Custom GPT Actions and other REST API clients

Both endpoints create Jira issues, but use different protocols. The MCP endpoint uses JSON-RPC format, while the REST endpoint uses standard HTTP/JSON.

Prerequisites

  • Node.js (v16 or higher)
  • npm or yarn
  • A Jira account with API access
  • Postman (or any HTTP client) for testing

Installation

  1. Clone the repository:```bash
    git clone https://github.com/coollikeabreeze/jira-mcp-server.git
    cd jira-mcp-server

2. Install dependencies:```bash
npm install

Configuration

Environment Variables

Create a .env file in the root directory with the following variables:```env

YOUR JIRA ACCOUNT & TOKEN INFORMATION

JIRA_BASE_URL=https://your-domain.atlassian.net
JIRA_EMAIL=your-email@example.com
JIRA_API_TOKEN=your-api-token
JIRA_PROJECT_KEY=YOUR_PROJECT_KEY
PORT=3000


**Getting your Jira API Token:**

1. Go to Atlassian Account Settings
2. Click "Create API token"
3. Copy the token and add it to your `.env` file

### SSL Certificates

The server uses HTTPS with self-signed certificates. Generate them using:```bash
openssl req -x509 -newkey rsa:2048 -keyout server.key -out server.cert -days 365 -nodes -subj "/C=US/ST=State/L=City/O=Organization/CN=localhost"

This will create:

  • server.key - Private key (already in .gitignore)
  • server.cert - Certificate file (already in .gitignore)

Running the Server

Start the development server:```bash
npm run dev


The server will start on `https://localhost:3000/mcp` (or your configured PORT).

## Usage

### As an MCP Server

The primary use case is as an MCP server. Connect using any MCP-compatible client:

#### Testing with Postman MCP Client

Postman has built-in support for MCP servers via the MCP Client. Here's how to connect:

1. **Open Postman MCP Client**:

   - In Postman, navigate to the MCP Client section
   - Click "Add Server" or "Connect to Server"

2. **Configure HTTPS Connection**:

   - Select **HTTPS** as the connection type
   - Server URL: `https://localhost:3000/mcp`
   - Port: `3000` (or your configured PORT)
   - **Important**: Since we're using self-signed certificates, you may need to:
     - Accept the certificate warning, or
     - Go to Postman Settings → General and temporarily disable "SSL certificate verification"

3. **Connect to the Server**:
   - Click "Connect" to establish the connection
   - Postman will automatically discover available tools from the MCP server

### Using the create_jira_issue Tool

Once connected, you can use the `create_jira_issue` tool:

**Required parameters:**

- `summary` (string) - Issue summary/title
- `description` (string or ADF JSON object) - Issue description. Accepts:
  - **String**: Plain text description (will be converted to ADF format)
  - **ADF JSON object**: Atlassian Document Format for rich text (preferred). This is the format sent by Custom GPT Actions, supporting bold, italic, links, lists, and other formatting.
- `issuetype` (string) - Issue type name (e.g., "Task", "Bug", "Story")

**Optional parameters:**

- `parentKey` (string) - Parent issue key for subtasks
- `labels` (array of strings) - Labels to apply to the issue

**Example tool call:**

- Tool: `create_jira_issue`
- Arguments (with string description):```json
  {
    "summary": "Test Issue from Postman",
    "description": "This is a test issue created via the MCP server",
    "issuetype": "Task",
    "parentKey": "PROJ-123",
    "labels": ["test", "postman"]
  }
  ```

- Arguments (with ADF JSON description - used by Custom GPT Actions):```json
  {
    "summary": "Test Issue from GPT",
    "description": {
      "type": "doc",
      "version": 1,
      "content": [
        {
          "type": "paragraph",
          "content": [
            {
              "type": "text",
              "text": "This is a test issue with "
            },
            {
              "type": "text",
              "text": "rich text formatting",
              "marks": [
                {
                  "type": "strong"
                }
              ]
            }
          ]
        }
      ]
    },
    "issuetype": "Task",
    "labels": ["test", "gpt"]
  }
  ```

### Example Response```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Created Jira issue PROJ-456"
      }
    ],
    "meta": {
      "issueKey": "PROJ-456",
      "issueId": "12345",
      "url": "https://your-domain.atlassian.net/rest/api/3/issue/12345"
    }
  }
}

Error Handling

If there's an error, you'll receive a response like:json { "jsonrpc": "2.0", "id": 1, "error": { "code": -32603, "message": "Internal error", "data": "Jira error 400: ..." } }

Troubleshooting

  • SSL Certificate Error:
  • Accept the certificate warning when connecting, or
  • Temporarily disable SSL verification in Postman Settings → General
  • Connection Refused:
  • Ensure the server is running (npm run dev)
  • Verify the server URL matches: https://localhost:3000/mcp
  • Check that the port matches your PORT environment variable
  • MCP Client Connection Issues:
  • Make sure you're using the HTTPS option in Postman MCP Client
  • Verify the server is accessible at the configured URL
  • Jira API Errors:
  • Check that your API token and project key are correct in the .env file
  • Verify your Jira account has permissions to create issues in the project
  • Missing Environment Variables:
  • Verify all required variables are set in your .env file
  • Restart the server after updating .env file

Deployment to Render

This server can be deployed to Render for a public HTTPS endpoint.

Prerequisites

  • A Render account (free tier available)
  • Your repository pushed to GitHub (or connected to Render)

Deployment Steps

  1. Connect Repository to Render:
  • Go to Render Dashboard
  • Click "New +" → "Web Service"
  • Connect your GitHub repository
  • Select the jira-mcp-server repository
  1. Configure the Service:
  • Name: jira-mcp-server (or your preferred name)
  • Environment: Node
  • Build Command: npm install && npm run build
  • Start Command: npm start
  • Plan: Free (or choose a paid plan)
  1. Set Environment Variables:
    Add the following environment variables in Render's dashboard:
  • JIRA_BASE_URL - Your Jira instance URL (e.g., https://your-domain.atlassian.net)
  • JIRA_EMAIL - Your Jira account email
  • JIRA_API_TOKEN - Your Jira API token
  • JIRA_PROJECT_KEY - Your Jira project key
  • USE_HTTPS - Set to false (Render handles HTTPS termination)
  • NODE_ENV - Set to production
  1. Deploy:
    - Click "Create Web Service"
    - Render will automatically build and deploy your service
    - Your service will be available at https://your-service-name.onrender.com/mcp

Using render.yaml (Alternative)

If you prefer configuration as code, you can use the included render.yaml file:

  1. Push your code to GitHub (make sure render.yaml is included)
  2. In Render Dashboard, go to "New +" → "Blueprint"
  3. Connect your repository
  4. Render will automatically detect and use render.yaml
  5. Set the environment variables (marked as sync: false in the YAML)

Post-Deployment

After deployment, your MCP server will be available at:

  • MCP Endpoint: https://your-service-name.onrender.com/mcp
  • REST API Endpoint: https://your-service-name.onrender.com/api/create-issue

Testing the MCP Endpoint:

  • Use Postman MCP Client or any MCP-compatible client
  • Server URL: https://your-service-name.onrender.com/mcp
  • Connection Type: HTTPS (no certificate warnings since Render provides valid SSL)

Testing the REST API Endpoint:

  • Use any HTTP client or integrate as a Custom GPT Action
  • Endpoint: https://your-service-name.onrender.com/api/create-issue
  • Requires Bearer token authentication (set API_KEY in Render)

As a Custom GPT Action

This MCP server also exposes a REST API endpoint compatible with Custom GPT Actions, allowing you to integrate Jira issue creation directly into ChatGPT.

Setup Steps:

  1. Deploy to Render (see Deployment section below)
  2. Copy the OpenAPI Schema: Copy the contents of openapi.yaml from your repository
  3. Add to Custom GPT: In your Custom GPT configuration, go to Actions → Create new action → Paste the schema
  4. Configure Authentication:
    - Select "Bearer" authentication
    - Enter your API_KEY value (set in Render environment variables)
  5. Description Format: When using Custom GPT Actions, the description field will be automatically sent as ADF JSON format, enabling rich text formatting in Jira issues (bold, italic, links, lists, etc.)

Endpoints:

  • /mcp - MCP protocol endpoint (for MCP clients)
  • /api/create-issue - REST API endpoint (for Custom GPT Actions)

Development

The server uses:

  • Express.js for the HTTP server
  • Model Context Protocol SDK for MCP protocol handling
  • TypeScript for type safety

License

ISC

常见问题

5 问
答案由本站依据条目字段整理,不引用上游原文
Jira MCP Server Af59130e 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Jira MCP Server Af59130e 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Jira MCP Server Af59130e 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Jira MCP Server Af59130e 需要 API Key 吗?

资料标注需要Token认证,使用前准备好对应凭据,并按最小权限配置。

Jira MCP Server Af59130e 能提供哪些能力?

资料显示约 1 个工具;能力标签包括 Jira集成、问题管理、TypeScript、API集成、自动化。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。