Skip to main content
Glama
Jira MCP Server

Jira MCP Server

by KS-GEN-AI

Jira 通信服务器 MCP 服务器

与 Jira 交谈

这是一个基于 TypeScript 的 MCP 服务器,提供与 Jira 交互的工具。它通过以下方式演示了 MCP 的核心概念:

  • 执行 JQL 查询的工具

  • 用于创建、编辑和删除 Jira 票证的工具

  • 列出 Jira 项目和状态的工具

特征

Related MCP server: JIRA MCP Server

Jira 工具

execute_jql

  • 目的:运行 JQL 查询。

  • 参数: jql , number_of_results (默认值:1)。

get_only_ticket_name_and_description

  • 目的:获取票证名称和描述。

  • 参数: jql , number_of_results (默认值:1)。

create_ticket

  • 目的:创建 Jira 票证。

  • 参数: project.key 、 summary 、 description 、 issuetype.name 、 parent (可选)。

list_projects

  • 目的:列出 Jira 项目。

  • 参数: number_of_results (默认值:1)。

delete_ticket

  • 目的:删除一张票。

  • 参数: issueIdOrKey 。

edit_ticket

  • 目的:修改票证。

  • 参数: issueIdOrKey 、 summary (可选)、 description (可选)、 labels (可选)、 parent (可选)。

get_all_statuses

  • 目的:检索所有状态。

  • 参数: number_of_results (默认值:1)。

assign_ticket

  • 目的:将票分配给用户。

  • 参数: accountId 、 issueIdOrKey 。

query_assignable

  • 目的:查找项目中可分配的用户。

  • 参数: project_key 。

add_attachment

  • 目的:向票证添加附件。

  • 参数: issueIdOrKey 、 imageUrl 。

发展

安装依赖项:

npm install

构建服务器:

npm run build

对于使用自动重建的开发:

npm run watch

安装

要与 Claude Desktop 一起使用,请添加服务器配置:

在 MacOS 上: ~/Library/Application Support/Claude/claude_desktop_config.json在 Windows 上: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "Jira communication server": {
      "command": "node",
      "args": [
        "/PATH_TO_THE_PROJECT/build/index.js"
      ],
      "env": {
        "JIRA_URL": "https://XXXXXXXX.atlassian.net",
        "JIRA_API_MAIL": "Your email",
        "JIRA_API_KEY": "KEY_FROM : https://id.atlassian.com/manage-profile/security/api-tokens"
      }
    }
  }
}

调试

由于 MCP 服务器通过 stdio 进行通信,调试起来可能比较困难。我们推荐使用MCP Inspector ,它以包脚本的形式提供:

npm run inspector

检查器将提供一个 URL 来访问浏览器中的调试工具。

Available Tools

11 tools
add_attachment_from_confluenceC

Add an attachment to a ticket on Jira from a Confluence page by its name on the api /rest/api/3/issue/{issueIdOrKey}/attachments. Do not use markdown in your query.

Inputs: issueIdOrKey (required), pageId (required), attachmentName (required).

add_attachment_from_public_urlA

Add an attachment from a public url to a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}/attachments. Do not use markdown in your query.

Inputs: issueIdOrKey (required), imageUrl (required).

assign_ticketB

Assign a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}/assignee. Do not use markdown in your query.

Inputs: accountId (required), issueIdOrKey (required).

create_ticketC

Create a ticket on Jira on the api /rest/api/3/issue. Do not use markdown in any field.

Inputs: project (required), summary (required), description (required), issuetype (required), +1 more.

delete_ticketC

Delete a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}. Do not use markdown in your query.

Inputs: issueIdOrKey (required).

edit_ticketC

Edit a ticket on Jira on the api /rest/api/3/issue/{issueIdOrKey}. Do not use markdown in any field.

Inputs: issueIdOrKey (required), summary, description, labels, +1 more.

execute_jqlC

Execute a JQL query on Jira on the api /rest/api/3/search/jql. Do not use markdown in your query.

Inputs: jql (required), number_of_results.

get_all_statusesC

Get all the status on Jira on the api /rest/api/3/status. Do not use markdown in your query.

Inputs: number_of_results.

get_only_ticket_name_and_descriptionC

Get the name and description of the requested tickets on the api /rest/api/3/search/jql. Do not use markdown in your query.

Inputs: jql (required), number_of_results.

list_projectsC

List all the projects on Jira on the api /rest/api/3/project. Do not use markdown in your query.

Inputs: number_of_results.

query_assignableC

Query assignables to a ticket on Jira on the api /rest/api/3/user/assignable/search?project={project-name}. Do not use markdown in your query.

Inputs: project_key (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 11 tools

    Disambiguation4/5

    Most tools have distinct purposes targeting specific Jira operations like create, edit, delete, assign, query, and list. However, 'execute_jql' and 'get_only_ticket_name_and_description' both query tickets via JQL, creating some overlap that could cause confusion, though their descriptions clarify different output focuses.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case throughout, such as 'create_ticket', 'assign_ticket', and 'list_projects'. This predictability makes it easy for agents to understand and navigate the tool set without naming conflicts.

    Tool Count5/5

    With 11 tools, the count is well-scoped for a Jira server, covering core operations like ticket management, attachments, queries, and project listing. Each tool appears to serve a specific function without unnecessary bloat, fitting typical server tool ranges.

    Completeness4/5

    The tool set provides good coverage for Jira workflows, including CRUD operations for tickets, assignment, attachments, and project/status queries. Minor gaps exist, such as missing tools for comments, transitions, or watchers, but core functionalities are present and agents can likely work around these omissions.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that enables AI assistants like Claude to interact with Jira, allowing for project management tasks such as listing projects, searching issues, creating tickets, and managing sprints through natural language queries.
      7
      1,667 npm
      2
      TypeScript
      MIT