yandex-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
- 0 ★ on the repository
- Last commit
Broad access
Why this level
- A Tracker token gives reading and changing issues, comments and worklogs on your behalf, and changes are visible to colleagues
- Confirmation before writing lies with the MCP client, so without configured confirmation an agent can change issues immediately
Install
- Works in
- Services
Manual install
uv sync && uv run yandex-tracker-mcpRun in the repository folder after filling `.env`.
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- A Tracker token gives reading and changing issues, comments and worklogs on your behalf, and changes are visible to colleagues
- Confirmation before writing lies with the MCP client, so without configured confirmation an agent can change issues immediately
This is third-party code. Review the repository files before installing.
What it does
The server gives an agent 30 tools: 20 for reading and 10 for changing data. You can read issues and search, comments, queues, status transitions, checklists, worklogs, users, queue fields, issue types, priorities and resolutions. Changing tools create and update issues, add comments, execute transitions, and manage checklist items and worklog entries. Time reports are built by `get_issue_time_report` for one issue and `get_time_report` for a Tracker query language request with `date_from` and `date_to`. The server converts ISO 8601 durations into minutes, counting a working day as 8 hours and a week as 40 hours. A report covers up to 200 issues and 500 entries per issue, and `truncated: true` comes back when the limit is hit. Yandex 360 and Yandex Cloud organizations are supported with OAuth and IAM sign-in.
Who it is for. Project managers and teams on Yandex Tracker who keep issues, checklists and time tracking and want to manage them from an agent chat.
Good fit when
- You need team costs for a queue over a period split by employee and issue
- An issue checklist must be reviewed: completion percent, overdue items, assignees
- An agent creates an issue and first requests valid types, priorities and queue fields
- Issue worklogs are compared with the original estimate and the deviation is calculated
Not a fit when
- You need Tracker boards, sprints and projects: the toolset does not cover them
- You need a ready cloud connector: this server is launched yourself with `uv`
- You have no OAuth or IAM token and organization ID: sign-in is impossible without them
Example request
Show team costs for the BACKEND queue from September 1 to 30 split by employee and issueMCP
- Transport
- stdio
- Authentication
- OAuth
Environment variables
TRACKER_TOKENsecret- Tracker OAuth token, use either it or an IAM token
TRACKER_IAM_TOKENsecret- Yandex Cloud IAM token instead of OAuth
TRACKER_ORG_ID- Yandex 360 organization ID
TRACKER_CLOUD_ORG_ID- Yandex Cloud organization ID
Limitations
It needs Python 3.11 or newer and uv. Exactly one sign-in method is allowed, `TRACKER_TOKEN` or `TRACKER_IAM_TOKEN`, and exactly one organization ID, `TRACKER_ORG_ID` or `TRACKER_CLOUD_ORG_ID`. Changing tools ask the client to show a plan and get confirmation first, but the client enforces this and the server requires no confirmation. A working day of 8 hours and a week of 40 hours are hard-coded. MIT license, the last commit in September 2026, no stars.
How to disable. Remove the `yandex-tracker` entry from `.cursor/mcp.json` or client settings and revoke the OAuth token in the Yandex account settings.
FAQ
Which sign-in methods are supported?
An OAuth token in `TRACKER_TOKEN` or an IAM token in `TRACKER_IAM_TOKEN`. Use exactly one of them.
How do I specify the organization?
`TRACKER_ORG_ID` for a Yandex 360 organization or `TRACKER_CLOUD_ORG_ID` for Yandex Cloud, again exactly one ID.
In what format is time recorded?
As an ISO 8601 duration, for example `PT1H30M`. The server converts values to minutes and counts a day as 8 hours.
What does the checklist report show?
`get_checklist_report` calculates the completion percent, shows open and overdue items and groups them by assignee.
How do I connect the server to Cursor?
Add an entry to `.cursor/mcp.json` with the `uv` command, arguments `--directory <path> run yandex-tracker-mcp` and the `TRACKER_TOKEN`, `TRACKER_ORG_ID` variables.
Discussion
No questions or reviews yet.
Related
All Yandex Tracker toolsA Yandex Tracker MCP server: queues, issues, comments, status transitions, sprints and search in Tracker query language
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
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
tracker-mcp
traker-mcp
A Yandex Tracker MCP server with 187 tools and a skill: issues, queues, boards, sprints and automation over API v3, with a read-only mode
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 with 146 tools
ya-tracker-mcp
Full Yandex Tracker API coverage via uvx: 146 tools for issues, projects, portfolios, goals, boards, sprints and worklogs
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: Tracker issues, checklists and time tracking (this card) | no | OAuth | 0 | |
| Yandex Tracker MCP Server | no | key is optional | 123 | adds checklist and team time reports normalised to minutes |
| A basic Yandex Tracker MCP server | no | API key | 0 | another independent Tracker server with a focus on checklists and worklogs |
README in short
The README lists capabilities, a quick start, connecting to Cursor, lists of read and write tools, descriptions of checklist and time reports, reference tools and links to Tracker documentation.