yandex-tracker-mcp
An MCP server for Yandex Tracker with 32 tools: issues, sprints, projects, checklists and time tracking in one server
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Can bulk-edit several issues in one bulk_update_issues call
- Can create, move and transition issues between statuses without a separate confirmation step
Install
Manual install
git clone https://github.com/in5pirer/yandex-tracker-mcp.git && cd yandex-tracker-mcp && pip install -r requirements.txt && cp .env.example .envFill in .env with your credentials after installing.
This is third-party code. Review the repository files before installing.
What it does
The server covers a wide slice of the Yandex Tracker API: creating, editing, moving and bulk-updating issues, search with pagination and a count-only mode, comments, transitions and changelog history, issue links, attachments, ISO 8601 worklog time tracking, checklists with progress, queue and component references, users, boards with sprints, and projects. Each tool group has a table with a description and call examples in the README, including ready Tracker Query Language phrases.
Who it is for. For teams that need the widest possible Tracker coverage in one server: from checklists to time tracking and sprints.
Good fit when
- You need checklists, time tracking and board sprints, not just basic issues
- You need a bulk update of several issues in one call
- You work through Cursor and are fine setting up the Python server manually
Not a fit when
- You need a ready package without git clone and pip install
- A few basic operations are enough, broad coverage would only complicate tool choice
Example request
Create an issue in the SUPPORT queue with critical priority, bug and urgent tags, and a 2026-03-31 deadlineLimitations
No official package, manual install via git clone, pip install -r requirements.txt and filling in .env. Cursor must be restarted after changing server.py. Community project, not from Yandex.
How to disable. Remove the yandex-tracker block from ~/.cursor/mcp.json or your client's config.
MCP
- Transport
- stdio
- Authentication
- API key
| Environment variables | |
|---|---|
| YANDEX_TRACKER_TOKEN required, secret | OAuth token from oauth.yandex.ru |
| YANDEX_TRACKER_ORG_ID | Organization ID for Yandex 360, one of two required together with CLOUD_ORG_ID |
| YANDEX_TRACKER_CLOUD_ORG_ID | Cloud organization ID for Yandex Cloud |
Security check
- Can bulk-edit several issues in one bulk_update_issues call
- Can create, move and transition issues between statuses without a separate confirmation step
README in short
The Russian README lists 32 tools by section: issues, search, comments, status and history, links, attachments, time tracking, checklists, queues and components, users, boards and sprints, projects. It shows pip-based installation, .env setup for cloud and non-cloud organizations, Cursor configuration and Tracker Query Language examples.
FAQ
How do I log time on an issue?
The add_worklog tool accepts an issue_id, an ISO 8601 duration (e.g. PT2H30M) and a comment.
Can several issues be updated at once?
Yes, bulk_update_issues accepts a list of issue_ids and a shared set of fields to change in one call.
Related
A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review
Skills for real engineers by Matt Pocock
Skills For Real Engineers
Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture
GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation
Reference MCP servers
Model Context Protocol servers
Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything