Yandex Tracker MCP with a report scheduler
Yandex Tracker MCP
A Python Yandex Tracker MCP server with issues, a recurring report scheduler and a SQLite run history
- 0 ★ on the repository
- Last commit
Broad access
Why this level
- Creates, updates and closes issues in the real Tracker when confirmed=true
- Scheduled reports can be sent to an external Telegram bot with real issue data
- Stores the OAuth token and API key in .env
Install
- Works in
- Services
Manual install
py -3.12 -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -e ".[dev]"Local install on Windows; venv activation commands differ on Linux and macOS.
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Creates, updates and closes issues in the real Tracker when confirmed=true
- Scheduled reports can be sent to an external Telegram bot with real issue data
- Stores the OAuth token and API key in .env
This is third-party code. Review the repository files before installing.
What it does
The server manages Tracker issues: creating, reading, updating, searching and closing them through available status transitions, since Tracker has no way to delete a single issue (per Yandex's help, an unwanted issue is closed with a resolution or moved to a queue that is then deleted as a whole). All write calls require confirmed=true, and creation is protected from duplicates via a unique field. A separate tool group creates once, interval or cron schedules that collect a queue summary: total issues, open, overdue, critical and unassigned, saves the report and run to SQLite, and optionally hands the finished Markdown file to an external Telegram bot over a protected endpoint. A three-step composition of search, summarize and save lets the agent take an issue snapshot, compute aggregates and save an artifact for another MCP server.
Who it is for. For teams that need not only Tracker issue operations but also recurring automated queue summaries.
Good fit when
- You need a daily or weekly report on overdue and critical queue issues on a schedule
- You need to safely create and transition issues with protection from accidental duplicates
- You need to compose search, summarize and save an issue snapshot to hand off to another service
Not a fit when
- You need boards and sprints: the server focuses on issues and reports, not board management
- You need direct Telegram sending: the server itself does not send messages, it calls a separate bot service
Example request
Find open issues in the AI queue, summarize the overdue and critical ones and save the reportMCP
- Transport
- http
- Authentication
- API key
Environment variables
YANDEX_TRACKER_TOKENrequired, secret- OAuth token with tracker:write scope
YANDEX_ORG_IDrequired- Yandex 360 or cloud organization ID, sent as X-Org-ID or X-Cloud-Org-ID
YANDEX_DEFAULT_QUEUErequired- Default queue for test runs and reports
MCP_API_KEYrequired, secret- Secret protecting the server's public endpoint
TELEGRAM_BOT_SERVICE_URL- Address of an external Telegram bot service for report delivery
Limitations
The scheduler and Telegram delivery only work with a separate bot service, which is not part of this repository. Requires an OAuth app with tracker:write scope and a separate MCP_API_KEY to protect its own endpoint. The Docker SQLite storage needs to be kept as a persistent volume.
How to disable. Stop the yandex-tracker-mcp container with docker compose down or remove it from your MCP client config.
FAQ
Can the server delete an issue?
No, Tracker has no way to delete a single issue; it can only be closed with a resolution or deleted along with its queue. The server calls cancel_issue instead and closes or cancels the issue via a workflow transition.
How can I test without risking real issues?
Run the server with TRACKER_BACKEND=mock, so every call goes to a mock backend instead of the real Tracker.
Discussion
No questions or reviews yet.
Related
All Yandex Tracker toolsyandex-tracker-mcp: Tracker issues, checklists and time tracking
yandex-tracker-mcp
An independent Python MCP server for the Yandex Tracker REST API v3: issues, transitions, checklists, worklogs and time reports
A Yandex Tracker MCP server: queues, issues, comments, status transitions, sprints and search in Tracker query language
Yandex Tracker MCP in TypeScript
yandex-tracker-mcp
A TypeScript Yandex Tracker MCP server with boards, sprints and bulk issue operations
Tracker report Telegram delivery MCP
Telegram Delivery MCP
A companion MCP server that takes a finished Yandex Tracker report and sends it to Telegram through an existing bot service
Yandex Tracker MCP without PII
Yandex Tracker MCP
A Yandex Tracker MCP server that deliberately withholds assignees and authors, returning only a whitelist of issue, comment and link fields
Yandex Tracker MCP: 23 tools for issues and files
yandex_tracker_mcp
A compact Python Yandex Tracker server: 23 tools, attachments and a one-variable read-only mode
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Yandex Tracker MCP with a report scheduler (this card) | no | API key | 0 | |
| Yandex Tracker MCP Server | no | key is optional | 123 | issues and sprints |
| Yandex Tracker MCP: typed and raw v3 tools | no | OAuth | 0 | typed and raw calls |
| Yandex Tracker MCP in TypeScript | no | OAuth | 0 | boards, sprints |
README in short
The README lists 12 tools, explains the confirmed and unique safeguards, gives a quick mock-backend run with no risk to real issues, production setup via .env and Docker, a section on getting Tracker access with an OAuth app, the scheduler with Telegram delivery, and a three-step search, summarize, save composition for handing an artifact to another MCP server.