Skip to content
MCP server

Yandex Tracker MCP

MCP server giving AI assistants read and write access to Yandex Tracker issues and queues

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, API, self-hosted
Runs
Locally
Version
0.8.2
Listing updated
today

Similar MCP servers

About Yandex Tracker MCP

Yandex Tracker MCP is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

The server wraps the Yandex Tracker API so an MCP-capable assistant can search and query issues with Tracker's query language, read and change issues, and manage comments, worklogs, attachments and status transitions. It also exposes queues, boards, sprints, saved filters, projects and portfolios, plus user lookups.

Access can be restricted per queue with a queue allow-list, and a read-only mode disables write tools. Authentication supports a personal OAuth token, an IAM token, a service account, or an OAuth flow for multi-user deployments. Redis can be enabled for caching and for persistent OAuth storage.

It suits teams already tracking work in Yandex Tracker who want an assistant to triage, summarise or update tickets. The README documents setup for Claude Desktop, Claude Code, Cursor, Windsurf, Zed, VS Code Copilot and other MCP clients, via uvx or a Docker image.

Install

Run in a terminal

claude mcp add yandex-tracker-mcp -- docker run -i --rm ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2

Add to claude_desktop_config.json

{
  "mcpServers": {
    "yandex-tracker-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "yandex-tracker-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "yandex-tracker-mcp": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "yandex-tracker-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "yandex-tracker-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2"
      ]
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (14)

Taken from the project documentation; the running server may differ.

issues_find
Search issues using Yandex Tracker Query Language.
issues_count
Count issues matching a query.
issue_get
Retrieve detailed issue information by ID.
issue_create
Create a new issue in a queue.
issue_update
Update an existing issue.
issue_move
Move an issue to a different queue.
issue_add_comment
Add a comment to an issue.
issue_add_worklog
Add a worklog entry to an issue.
issue_execute_transition
Execute a status transition for an issue.
issue_close
Close an issue with a resolution.
issue_get_changelog
Get the change history of an issue.
queues_get_all
List all available queues.
queue_get_fields
Get global and local fields for a queue.
users_search
Search users by login, email or real name.

What it does

Issue lifecycle tools
Create, read, update and move issues, and run status transitions or close them with a resolution.
Tracker query search
Find and count issues using Yandex Tracker Query Language or a saved filter.
Worklogs and comments
Log time, edit worklog entries, and add, update or delete comments with user summons.
Queue and field metadata
List queues, their fields, statuses, issue types, priorities and resolutions to support issue creation.
Access restrictions
Limit which queues the assistant can touch and disable all write tools with a read-only setting.
Multiple auth methods
Works with a personal token, IAM token, service account or OAuth 2.0 flow.

Good for

  • Asking an assistant to summarise open issues in a queue or sprint
  • Creating well-formed tickets after checking required fields
  • Logging time spent on issues from a chat session
  • Reviewing an issue's changelog to see who changed what and when
  • Bulk-reading issue data for reporting through issues_count and issues_find

Pricing

Open source

Open-source MCP server; uses your own Yandex Tracker account.

Yandex Tracker MCP FAQ

Which transport does the server support?

The registry entry lists stdio, and the README also describes streamable-http. SSE is mentioned as deprecated.

How can write access be disabled?

Setting TRACKER_READ_ONLY=true makes write tools unavailable.

What authentication options are available?

A static OAuth token, an IAM token, service account credentials, or an OAuth 2.0 flow, with a stated priority order between them.

Is Yandex Tracker MCP free?

Yes. Yandex Tracker MCP is open source, so you can use and self-host it for free.

How do I add Yandex Tracker MCP to Claude Code?

Run this command in your terminal: claude mcp add yandex-tracker-mcp -- docker run -i --rm ghcr.io/aponkratov/yandex-tracker-mcp:0.8.2

What are the best alternatives to Yandex Tracker MCP?

The closest alternatives to Yandex Tracker MCP are Desk365 MCP by usefulapi, Zammad MCP by usefulapi, Uptrack MCP and Submittable MCP by usefulapi.

Where this comes from

  • Description: written from the project's README and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers