Google Play MCP

create_release

Publish Google Play releases by assigning build version codes to tracks with draft, completed, staged, or halted statuses; use dryRun to validate before publishing.

Instructions

Put build(s) on a track as a release. status: 'draft' (saved, not rolled out), 'completed' (full rollout), 'inProgress' (staged rollout — requires userFraction, e.g. 0.1 = 10%), 'halted'. versionCodes come from upload_bundle / list_bundles. Production releases are gated by PLAY_MCP_ALLOW_PRODUCTION_RELEASE. Set dryRun:true to have Google validate the release without publishing.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "packageName": "<packageName>",
      "track": "<track>",
      "versionCodes": "<versionCodes>",
      "status": "<status>"
    },
    "name": "create_release"
  }
}

Input Schema

Name	Required	Description
`name`	No	Release name (defaults to the versionName)
`track`	Yes	Track name: internal, alpha (closed testing), beta (open testing), production, a custom closed-testing track name, or a form-factor track such as wear:production
`dryRun`	No	Preview only: open a temporary edit, apply, validate, then delete it. Nothing is published (default false). Ignored when editId is set.
`editId`	No	Optional: an open edit from insert_edit. The change is applied inside that edit and NOT committed — batch several changes, then call commit_edit.
`status`	Yes
`packageName`	Yes	Application id (package name), e.g. com.example.app
`releaseNotes`	No	What's new, per language (max 500 chars each)
`userFraction`	No	Staged rollout fraction, strictly between 0 and 1 (only with inProgress/halted)
`versionCodes`	Yes	Version codes in this release (include any you want to retain)
`countryTargeting`	No	{ countries: ['US', ...], includeRestOfWorld } — production inProgress releases only
`inAppUpdatePriority`	No	0–5 (default 0)
`changesNotSentForReview`	No	Commit option: keep the changes out of review until sent from Play Console. Google requires this for some apps and rejects it for others — set it only if a commit error asks for it.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the production gating env var, that dryRun validates without publishing, that editId applies changes without committing, and the unusual changesNotSentForReview constraint. It stops short of describing failure modes, idempotency, or what a successful call returns.

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

Conciseness4/5

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

A single dense paragraph that front-loads the core action and then walks through status values, prerequisites, and the dryRun escape hatch. Every clause carries information, though the prose is compressed enough that a status-by-status layout would read more easily.

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 12-parameter mutation tool with no annotations and no output schema, the description covers the high-risk behaviors (production gating, staged rollout fraction, non-committing edit mode) that an agent must know before calling. Remaining gaps, such as conflict handling and return shape, are modest given the rich schema.

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 coverage is already 92%, so the baseline is 3, but the description still adds real meaning the schema lacks: the semantics of each status value and the requirement linking inProgress/halted to userFraction. It also clarifies dryRun's interaction with editId.

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

Purpose4/5

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

The opening sentence states a specific verb and resource: 'Put build(s) on a track as a release.' It also names where versionCodes originate (upload_bundle / list_bundles), which orients the agent in the workflow. It does not explicitly distinguish itself from promote_release, so it falls short of a 5.

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 clear conditional guidance: which status value to pick and what each means, that inProgress requires userFraction, and that production releases need PLAY_MCP_ALLOW_PRODUCTION_RELEASE. It does not state when to use this instead of promote_release or complete_rollout, so alternative-routing guidance is incomplete.

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

Deploy Server