Yandex Tracker MCP Server

Overview Schema Source Related Servers Discussions Admin

Create Issue

issue_create

Create a new task in a Yandex Tracker queue. Specify the queue and summary, then add optional details such as description, assignee, priority, tags, and components.

Instructions

Create an issue (in russian - 'задача') in a Yandex Tracker queue. There is no template argument: read a template with issue_templates_get_all and copy its fieldTemplates values into these arguments field by field. The returned version goes stale at once, as queue triggers bump it - re-read it with issue_get.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No	Issue tags as array of strings.
`type`	No	Issue type: an object with 'id' (type ID) and/or 'key' (e.g., 'bug', 'task'), or the bare key/ID (from get_issue_types tool).
`queue`	Yes	Queue key where to create the issue (e.g., 'MYQUEUE')
`fields`	No	Additional fields to set, for those without a dedicated parameter above. Field ids come from `queue_get_fields` (schema.required=true marks the mandatory ones) or `get_global_fields`, which also lists system fields such as `parent` or `estimation` that the queue listing may omit. Keys are Tracker's own camelCase ids, e.g. 'storyPoints'. An entry here overrides the dedicated parameter of the same name. Values are sent as-is: reference fields want numeric IDs as numbers or {'id': ...} objects, since a bare string may be read as a name.
`parent`	No	Parent issue reference. Object with 'id' (parent issue ID) and/or 'key' (parent issue key like 'QUEUE-123'); when both are given Tracker resolves by 'id', or the bare key.
`sprint`	No	Sprint assignments. Array of objects, each with 'id' field containing the sprint ID (integer).
`project`	No	Project assignment. Object with 'primary' (int, main project shortId) and optional 'secondary' (list of ints, additional project shortIds).
`summary`	Yes	Issue title/summary
`assignee`	No	Assignee login or UID
`priority`	No	Issue priority: an object with 'id' (priority ID) and/or 'key' (e.g., 'critical', 'normal'), or the bare key/ID (from get_priorities tool).
`followers`	No	Issue followers/watchers. Array of objects, each with an 'id' field holding the user ID (uid) or login.
`components`	No	Queue components. Array of objects with either 'id' (numeric component ID, from queue_get_components or queue_get_metadata with expand=['components']) or 'name' (component name). Tracker resolves numbers as IDs and strings as names, so the object form is required to avoid a 422 on a numeric-looking name.
`description`	No	Issue description (use markdown formatting)
`markup_type`	No	Markup type for description text. Use 'md' for YFM (markdown) markup.	md

Output Schema

TableJSON Schema

Name	Required	Description
`key`	No
`epic`	No
`tags`	No
`type`	No
`spent`	No
`start`	No
`votes`	No
`boards`	No	Agile boards the issue shows up on. Tracker fills this in from the boards' own filters - an issue is not assigned to a board directly, so this is read-only. Use the board id with `board_get`, `board_get_columns` or `board_get_sprints`.
`parent`	No
`sprint`	No	Sprints the issue is in. Use `board_get_sprints` to look up the sprints of a board, and pass a sprint id to `issue_update` to move the issue between them.
`status`	No
`unique`	No
`summary`	No
`version`	No
`assignee`	No
`deadline`	No
`priority`	No
`createdAt`	No
`createdBy`	No
`updatedAt`	No
`updatedBy`	No
`components`	No
`estimation`	No
`description`	No
`storyPoints`	No
`previousStatus`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.10.0Sep 14, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=false already marks this as a write operation, and the description adds genuinely new behavioral context: the returned version goes stale at once because queue triggers bump it, plus a concrete mitigation (re-read with issue_get). This goes beyond what the schema or annotations convey. It could additionally disclose permission requirements or side effects like notifications, which keeps it at a 4 rather than a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero filler: the first states purpose, the second covers the template workflow, the third warns about version staleness. The core purpose is front-loaded ahead of the caveats, and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter create tool, the schema documents parameters, the output schema covers return values, and the description covers the workflow gotchas an agent would otherwise trip on. The template-argument absence and stale-version behavior are the critical non-obvious pieces, and both are addressed; no blocking information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 14 parameters, putting the baseline at 3. The description adds value by warning that no template parameter exists and instructing the agent to copy fieldTemplates values into the regular arguments field by field — preventing an invocation that passes a nonexistent argument.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Create an issue ... in a Yandex Tracker queue,' with the Russian synonym 'задача' added to remove ambiguity for a term that has multiple meanings. The verb clearly separates it from read/update/close siblings like issue_get, issue_update, and issue_close without needing to open any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance for the genuinely non-obvious workflow: there is no template argument, so the agent must read a template via issue_templates_get_all and copy its fieldTemplates values into these arguments field by field. It also routes post-create follow-up to issue_get when the version needs re-reading. It does not enumerate when-not-to-use conditions against mutation siblings, but the template case is the one that would actually cause a failed call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server