客户支持 · 开发者工具

Yandex Tracker MCP logo

Yandex Tracker MCP

aikts/yandex-tracker-mcp

Yandex Tracker MCP服务器是一个为AI助手提供与Yandex Tracker API交互的模型上下文协议服务,支持队列管理、用户管理、问题操作和高级搜索功能,提供安全认证访问和性能缓存。

安装

uvx yandex-tracker-mcp@latest

客户端配置

{
  "mcpServers": {
    "yandex-tracker": {
      "command": "uvx",
      "args": [
        "yandex-tracker-mcp@latest"
      ],
      "env": {
        "TRACKER_TOKEN": "<TRACKER_TOKEN>",
        "TRACKER_CLOUD_ORG_ID": "<TRACKER_CLOUD_ORG_ID>"
      }
    }
  }
}

环境变量

TRACKER_TOKENTRACKER_CLOUD_ORG_IDTRANSPORTOAUTH_ENABLEDOAUTH_CLIENT_IDOAUTH_CLIENT_SECRETMCP_SERVER_PUBLIC_URLOAUTH_SERVER_URLOAUTH_STOREREDIS_ENDPOINTREDIS_PORTREDIS_DB
作者
@aikts
分类
客户支持, 开发者工具
更新于
2026年10月6日

工具(40)

  • queue_get_metadata

    with expand: ["issueTypesConfig"] is where the resolutions valid for each issue type come from - issue_close needs one of them.

  • TRACKER_LIMIT_QUEUES

    and TRACKER_READ_ONLY_QUEUES apply through the component's queue: component_update and component_delete read the component first to learn it, and a component…

  • Arguments.

    Reads take entity_id and fields; the *_find tools take input, filter, order_by, order_asc, root_only, page, per_page.

  • users_search

    matches login and email exactly first and falls back to fuzzy name matching (80% similarity, at most the three best matches).

  • queue

    returns that queue's templates plus the ones bound to no queue, which are usable everywhere.

  • fields

    uses Tracker's own spelling (storyPoints, not story_points) and accepts any field name, a queue's local and the organization's custom fields included - pass…

  • include_description

    is ignored when description is listed in fields: naming it there is an explicit request for it.

  • per_page

    defaults to 100 and can be lowered when a page does not fit the context window.

  • queues_get_all

    Every queue the token may see; returns {values, hits, pages}

  • queue_get_tags

    The tags defined in the queue

  • queue_get_versions

    The queue's versions, with dates and status

  • queue_get_components

    The queue's components as full objects, with lead, auto-assign flag and version; queue_get_metadata with expand: ["components"] gives ids and names only

  • queue_create_version

    Create a version in the queue

  • queue_get_fields

    The fields configured on the queue, local ones included; schema.required marks the mandatory ones

  • component_get

    One component with queue, lead, assignAuto and version

  • component_create

    Create a component in a queue

  • component_update

    Change name, description, lead or auto-assign flag; omitted fields keep their value, clear_lead removes the lead

  • component_delete

    Delete a component

  • users_get_all

    A page of the organization's users; returns {values, hits, pages}

  • user_get

    One user by login or uid

  • user_get_current

    The user the current token belongs to

  • get_global_fields

    Every global field of the organization, with its schema and type

  • get_statuses

    Every issue status the organization defines

  • get_issue_types

    Every issue type, for the type argument of issue_create / issue_update

  • get_priorities

    Every priority, with id, key, name and order

  • get_resolutions

    Every resolution, for the resolution_id of issue_close

  • issue_templates_get_all

    The issue templates, with the fieldTemplates values they prefill; returns {values, hits, pages}

  • issue_template_get

    One issue template by id

  • comment_templates_get_all

    The comment templates, with the template text and its summonees / maillistSummonees

  • comment_template_get

    One comment template by id

  • boards_get_all

    The organization's agile boards; returns {boards, next_cursor}

  • board_get

    One board with autoFilterSettings (what it collects), estimateBy, useRanking and its working calendar

  • board_get_columns

    The board's columns with the issue statuses that land in each

  • board_get_sprints

    The board's sprints with status (draft, in_progress, released, archived) and planned/actual dates

  • issue_get

    One issue by key: the full record, the current version included

  • issue_get_url

    The web URL of an issue

  • issue_get_comments

    A page of comments, oldest first; returns {comments, next_cursor}

  • issue_add_comment

    Add a comment; summonees is what notifies a user, an @login in the text notifies nobody

  • issue_update_comment

    Edit a comment

  • issue_delete_comment

    Delete a comment

本页信息摘自该项目的 README。 查看 README

支持的客户端

该服务器 README 中提到的客户端:

查看全部
Claude Desktop logo

Claude Desktop

桌面端 · 免费增值 · Proprietary

Anthropic 官方推出的 Claude AI 桌面应用程序。支持 MCP 服务器以扩展功能。

WindowsMacOS
Cursor logo

Cursor

桌面端 · 免费增值 · Proprietary

首个代理式 IDE。Cursor 编辑器让开发者与 AI 的工作真正融合在一起,提供如魔法般的编码体验。

WindowsMacOSLinux
Windsurf logo

Windsurf

桌面端 · 免费增值 · Proprietary

首个代理式 IDE。Windsurf 编辑器让开发者与 AI 的工作真正融合在一起。

WindowsMacOSLinux
VS Code GitHub Copilot logo

VS Code GitHub Copilot

桌面端 · 免费增值 · MIT

VS Code 通过代理模式将 MCP 与 GitHub Copilot 集成,允许在你的代理编码工作流中直接与 MCP 提供的工具交互。在 Claude Desktop、工作区或用户设置中配置服务器,提供引导式 MCP 安装和安全处理输入变量中的密钥,避免泄露硬编码密钥。

WindowsMacOSLinuxWeb

相关 MCP 服务器

更多服务器
n8n Secure Workflow Automation for Technical Teams logo

n8n Secure Workflow Automation for Technical Teams

n8n-io/n8n

86.7k

n8n是一个面向技术团队的工作流自动化平台,结合了代码灵活性和无代码速度,提供400+集成、原生AI功能和公平代码许可,支持自托管或云端部署。

客户支持
MaxKB logo

MaxKB

1Panel-dev/MaxKB

16.2k

MaxKB是一款开源的AI助手,专为企业设计,支持RAG流程、工作流引擎和多模态交互,适用于智能客服、知识库等场景。

客户支持
MCP Server Chatsum logo

MCP Server Chatsum

chatmcp/mcp-server-chatsum

938

一个用于总结聊天记录的MCP服务器项目

客户支持
Linear MCP Server Cuq logo

Linear MCP Server Cuq

jerhadf/linear-mcp-server

280

Linear MCP Server是一个已弃用的Model Context Protocol服务器,用于通过MCP协议与Linear问题跟踪系统集成,允许LLM与Linear问题进行交互。

客户支持
MCP Knowledge Graph logo

MCP Knowledge Graph

shaneholloman/mcp-knowledge-graph

161

基于知识图谱的持久化记忆服务器,支持跨会话用户信息存储与检索

客户支持
Servicenow MCP logo

Servicenow MCP

osomai/servicenow-mcp

55

ServiceNow MCP服务器实现,为Claude提供与ServiceNow实例交互的桥梁

客户支持