Skip to main content
Glama

Connect developer console

connect_console

Links App Store Connect API keys or Google Play service accounts to enable console apps, publishing, and own-app metadata management.

Instructions

Connect an App Store Connect API key (apple: keyId, issuerId, private key .p8) or a Google Play service account (google: service-account JSON, optional package names; connecting the same service account again ADDS its package names to the saved ones). Play apps the key can see are found by themselves (Play Developer Reporting API); to add one it doesn't list to an already connected Play account, pass store google, accountId and packageNames WITHOUT a key: the app checks each package with the stored key and links the owner's app. Pass FILE PATHS (privateKeyPath / serviceAccountPath; files must be .p8/.pem/.json/.txt in the owner's Downloads, Desktop or Documents folder) so secrets never enter the conversation; the bridge reads them locally and the app stores them in the OS keychain. Credentials are never returned. Needed for console apps, publishing and own-app metadata.

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": {
      "store": "<store>"
    },
    "name": "connect_console"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyIdNoapple: API key id.
labelNoAccount label shown in the app.
storeYesStore: "apple" (App Store) or "google" (Google Play).
issuerIdNoapple: issuer id.
accountIdNogoogle: a connected Play account (list_console_apps, or details of a console_not_connected error) to add packageNames to with its stored key; no key needed.
packageNamesNogoogle: package names this account manages.
privateKeyPemNoapple: PEM contents (prefer privateKeyPath).
privateKeyPathNoapple: path to the AuthKey_XXXX.p8 file.
serviceAccountJsonNogoogle: service-account JSON contents (prefer serviceAccountPath).
serviceAccountPathNogoogle: path to the service-account JSON file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.3
    • addedInput schema / properties / accountId
      Added value: +{
      +  "description": "google: a connected Play account (list_console_apps, or details of a console_not_connected error) to add packageNames to with its stored key; no key needed.",
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. First observedv0.1.7

TDQS

A4/5.0
Behavior4/5

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

Well beyond the annotations, it discloses that secrets are read locally from disk, stored in the OS keychain, and never returned, plus the folder restriction on file paths. It also explains the non-idempotent behavior flagged by idempotentHint=false: reconnecting the same Google service account ADDS package names rather than replacing them. It does not state what happens on reconnecting an existing Apple key, which is the one behavioral gap.

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?

The size is proportionate to a 10-parameter, two-store tool and the primary action is front-loaded. It is a single dense paragraph with stacked parentheticals, so the Apple and Google paths are not visually separated, but no sentence is filler.

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?

With no output schema, the description still covers the security model, credential handling, both connection modes and app auto-discovery, which is what an agent needs to call it safely. The remaining gap is the effect of reconnecting an already-connected Apple key and what the call returns on success.

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 100%, so the baseline is 3; the description earns more by adding constraints absent from the schema, notably that files must be .p8/.pem/.json/.txt inside Downloads, Desktop or Documents, and that path parameters are preferred over inline secret contents. It also clarifies the key-less accountId + packageNames combination, which is the least obvious interaction in the schema.

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 description opens with a specific verb and two concrete resources: 'Connect an App Store Connect API key ... or a Google Play service account', and it names the credential artifacts (keyId, issuerId, .p8, service-account JSON). An agent immediately knows this establishes a store connection rather than listing or testing one. It stops short of naming siblings like add_console_apps or test_console, so the boundary is inferred rather than stated.

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?

It gives explicit trigger conditions ('Needed for console apps, publishing and own-app metadata') and a distinct secondary mode with its own precondition: pass store google, accountId and packageNames WITHOUT a key. It also points to list_console_apps and console_not_connected errors as the source of accountId. What is missing is when NOT to use it, e.g. versus test_console or disconnect_console.

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

Deploy Server

Other Tools