Skip to main content
Glama
Sign In
app-store-connect-mcp

app-store-connect-mcp

by devinwang
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

asset_upload_file

Uploads a local binary file to App Store Connect as step 2 of the asset protocol, sending chunks before finalization. Use it for screenshots, previews, and review attachments.

Instructions

Upload a local binary file to App Store Connect, following the 3-step asset protocol (screenshots, previews, review attachments, IAP review screenshots, app clip header images, game center images, etc.). This is step 2 (PUTting the chunks); afterwards call the resource's 'update' endpoint with { uploaded: true } to finalise (step 3). PREFERRED usage: pass assetType + assetId (the just-created asset) and the tool fetches the pre-signed uploadOperations server-side — the S3 upload signature never transits MCP output, so it can't be corrupted by secret redaction. Passing uploadOperations directly still works but is fragile: a signature relayed through MCP output may have been redacted.

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": {
      "filePath": "<filePath>"
    },
    "name": "asset_upload_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetIdNo
filePathYesAbsolute path to the file on the local disk.
assetTypeNo
uploadOperationsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that this is the PUT/chunk step of a multi-step mutation, that finalization happens elsewhere, and the subtle secret-redaction failure mode for signatures. That is meaningful behavioral context beyond any structured field.

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?

Front-loaded with the core action and protocol position before the parameter advice, and every sentence adds value. The parentheses listing asset types and the redaction rationale are dense but justified; slightly verbose but not wasteful.

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 mutation tool with no annotations and no output schema, the description explains the workflow, the required finalization step, and parameter pitfalls. It could say more about error/partial-upload behavior, but it is complete enough to call correctly.

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 only 25% (only filePath documented), but the description compensates by explaining assetType+assetId as a preferred pairing and characterizing uploadOperations as a fragile fallback. It doesn't detail offset/length/entityTag mechanics for the raw uploadOperations route, but overall it restores most parameter meaning.

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?

States a specific verb (upload) and resource (local binary file to App Store Connect) and enumerates the concrete asset types it serves. It also positions itself within a 3-step protocol, so an agent immediately knows its role versus sibling asset tools.

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?

Explicitly recommends the assetType+assetId route and warns that the uploadOperations route is fragile due to secret redaction. It also names the required follow-up ('update' endpoint with uploaded:true), leaving little to inference.

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