Skip to main content
Glama
aikts

Yandex Tracker MCP

Create Issue

issue_create

Create a new issue in a Yandex Tracker queue with a required summary, plus optional description, assignee, priority, components, and custom fields to match your workflow.

Instructions

Create a new issue in a Yandex Tracker queue. Check the queue's issue templates first (issue_templates_get_all with queue set): there is no template_id parameter, so a template is applied by copying its fieldTemplates values and description into the parameters below instead of inventing a structure of your own. Copy them field by field rather than wholesale: assignee comes as a user object, while this tool takes a login or uid, and Tracker does not expand the UI macros a template may contain ({{today}} and friends arrive literally). Prefer the dedicated parameters below over the fields map: they are sent in the same format issue_update uses, so a value that works here works there too. Note that the returned issue's version can be outdated as soon as it is returned - queue triggers and automation run right after creation and bump it - so do not reuse it for a follow-up issue_update; re-read the issue with issue_get or omit version.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoIssue tags as array of strings.
typeNoIssue type: an object with 'id' (type ID) and/or 'key' (e.g., 'bug', 'task'), or the bare key/ID (from get_issue_types tool).
queueYesQueue key where to create the issue (e.g., 'MYQUEUE')
fieldsNoAdditional fields to set during issue creation, for fields without a dedicated parameter above. Call `queue_get_fields` for the fields configured on the queue (schema.required=true marks the mandatory ones) and `get_global_fields` for the whole registry - system fields such as `parent` or `estimation` are settable but may be missing from the queue listing. Keys are Tracker field ids as those tools return them (camelCase, e.g. 'storyPoints'), which is also how they come back in issue responses. An entry here overrides the dedicated parameter of the same name. Values are sent to Tracker as-is: reference fields expect numeric IDs as numbers (or {'id': ...} objects), because a bare string may be resolved as a name.
parentNoParent 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.
sprintNoSprint assignments. Array of objects, each with 'id' field containing the sprint ID (integer).
projectNoProject assignment. Object with 'primary' (int, main project shortId) and optional 'secondary' (list of ints, additional project shortIds).
summaryYesIssue title/summary
assigneeNoAssignee login or UID
priorityNoIssue priority: an object with 'id' (priority ID) and/or 'key' (e.g., 'critical', 'normal'), or the bare key/ID (from get_priorities tool).
followersNoIssue followers/watchers. Array of objects, each with an 'id' field holding the user ID (uid) or login.
componentsNoQueue components. Array of objects with either 'id' (numeric component ID, from 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.
descriptionNoIssue description (use markdown formatting)
markup_typeNoMarkup type for description text. Use 'md' for YFM (markdown) markup.md

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNo
epicNo
tagsNo
typeNo
spentNo
startNo
votesNo
parentNo
sprintNo
statusNo
uniqueNo
summaryNo
versionNo
assigneeNo
deadlineNo
priorityNo
createdAtNo
createdByNo
updatedAtNo
updatedByNo
componentsNo
estimationNo
descriptionNo
storyPointsNo
previousStatusNo
Behavior5/5

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

Beyond the readOnlyHint annotation (which is false), the description discloses that queue triggers/automation run after creation and bump the version, making it unsafe to reuse. It also reveals that template macros like {{today}} are not expanded and that references may be sent as-is. This goes well beyond what annotations provide.

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?

The description is long but every sentence delivers unique value—no redundancy. It starts with the core purpose, then progressively layers operational details, maintaining a logical flow. It is concise relative to the depth of information conveyed.

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

Completeness5/5

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

Given the tool's complexity (14 parameters, output schema, interactions with templates, triggers, and versioning), the description covers all critical aspects: template usage, parameter preference, post-creation caveats, and type handling. It leaves no major gaps and provides enough context for correct invocation.

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?

While schema coverage is 100%, the description adds significant meaning around parameter usage: it explains how to derive values from templates, warns about field format differences (e.g., assignee as login/uid vs user object), and clarifies precedence of the fields map over dedicated parameters. This enhances understanding beyond the schema.

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 clearly states 'Create a new issue in a Yandex Tracker queue,' specifying the verb and resource. It distinguishes from sibling tools like issue_update, issue_close, and others by focusing on creation. The purpose is unambiguous.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use templates ('Check the queue's issue templates first...'), how to apply them (copy fieldTemplates values field by field), and warns against inventing structure. It also advises preferring dedicated parameters over the fields map and explains the consequence of version invalidation after creation. These are clear 'when/how' directives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aikts/yandex-tracker-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server