Yandex Tracker MCP in Yandex AI Studio
Яндекс Трекер в MCP Hub
A Yandex AI Studio MCP Hub template: an agent reads Tracker issue links, creates issues, comments and goals and bulk-changes statuses and queues
Broad access
Why this level
- Creates issues, comments and goals and bulk-changes Tracker statuses, projects and queues with a user's token
- The Tracker token is stored in the server settings in Yandex Cloud and grants access within its owner's rights
aistudio.yandex.ru/docs/ru/ai-studio/concepts/mcp-hub/templates
Install
- Works in
- Services
Manual install
In Yandex AI Studio open Agent Atelier, MCP servers, create a server from the Yandex Tracker template, enter the Tracker token with an OAuth or Bearer prefix and the organization ID, choose the tools and save. Then pass the server address in tools with type mcp in a Responses API request, together with an API key with the yc.serverless.mcpGateways.invoke scope.
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Creates issues, comments and goals and bulk-changes Tracker statuses, projects and queues with a user's token
- The Tracker token is stored in the server settings in Yandex Cloud and grants access within its owner's rights
This is third-party code. Review the repository files before installing.
What it does
The MCP Hub of the Yandex AI Studio platform includes a ready MCP server template for Yandex Tracker. The server is created under Agent Atelier, MCP servers: the template fixes the address, transport and auth type, and the user sets a name and access token and picks tools, up to 150 per server. The template's tools get issue links, create an issue, a comment and a goal, change issue and goal status and parameters, bulk-change issues, statuses, projects, portfolios and goals, and bulk-move issues to another queue. AI Studio agents connect such a server through the Responses API using its address and an API key with the yc.serverless.mcpGateways.invoke scope.
Who it is for. For teams on Yandex Tracker who build their own AI agents in Yandex AI Studio and want the agent to create and manage issues.
Good fit when
- An AI Studio agent should create Tracker issues and comments from a conversation or an email review
- You need to bulk-change statuses or move a batch of issues to another queue
- You need to connect the agent to Tracker goals, projects and portfolios
Not a fit when
- The agent runs in Claude Code, Cursor or Codex: the AI Studio docs describe connecting only through the Responses API and AI Studio agents
- You have no Yandex Cloud folder with the serverless.mcpGateways.editor role to create the server
Example request
Create an issue in the SUPPORT queue for this request and add a comment with a short analysisMCP
- Authentication
- OAuth
Environment variables
TRACKER_TOKENrequired, secret- Yandex Tracker token, passed in the token header with an OAuth or Bearer prefix
X_ORG_IDrequired- Organization ID (x-org-id) or cloud organization ID (x-cloud-org-id)
Limitations
Creating the server requires the serverless.mcpGateways.editor and iam.serviceAccounts.user roles, calling it requires serverless.mcpGateways.invoker. The Tracker token goes in the token header with an OAuth or Bearer prefix, the organization in the x-org-id or x-cloud-org-id header. To act as a service account you first contact Tracker support with the cloud organization and service account identifiers. The template's server address and pricing are not given in the public docs.
How to disable. Remove the MCP server from the agent's tools, delete it in AI Studio under Agent Atelier, MCP servers, and revoke the issued Tracker token.
FAQ
Can I enable only some tools?
Yes, after connecting the token you pick the tools for the server, up to 150 per server. Reading links and creating comments is enough for a first run.
Can it act as a service account?
Yes, but first contact Tracker support with the cloud organization and service account identifiers.
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 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 a report scheduler
Yandex Tracker MCP
A Python Yandex Tracker MCP server with issues, a recurring report scheduler and a SQLite run history
Yandex Tracker MCP in TypeScript
yandex-tracker-mcp
A TypeScript Yandex Tracker MCP server with boards, sprints and bulk issue operations
A Go MCP server for reading Yandex Tracker and Yandex Wiki: issues, queues, sprints, comments, pages and dynamic tables
Yandex Tracker MCP with one-click install
yandex-tracker-mcp
A Yandex Tracker MCP server with a .mcpb extension for Claude Desktop that needs no terminal: issues, comments, status transitions and a read-only mode
README in short
The MCP Hub templates page in the Yandex AI Studio docs lists Kontur.Focus, amoCRM, Yandex Tracker, Yandex Search and SourceCraft templates. For Tracker it gives the tool list, auth headers and a service account note. Related articles cover creating a server from a template, required roles, picking tools and connecting the server to an agent via the Responses API.