Skip to main content
Glama

upload_token

Needs sign-in (connect this server with OAuth, or pass an API key as the Authorization: Bearer header). Mints a short-lived bearer token for staging builds and media, without revealing the connection's sign-in token. It cannot publish. Stage a local build folder with Node 22+: download https://yougame.co/upload-build.mjs, then run node upload-build.mjs with YOUGAME_URL=https://yougame.co and YOUGAME_UPLOAD_TOKEN (from upload_token) or YOUGAME_API_KEY set. It applies the website's path fixes locally and streams files through POST /api/upload/start, PUT /api/upload/file (a file over 100 MB goes up in 64 MB parts through /api/upload/file/parts), and POST /api/upload/complete. The same limits as the website apply: up to 5 GB per build, 512 MB per file, 5,000 files. Pass the build folder or the build's .zip: the helper unpacks a zip on your machine and sends its files the same way. The result includes uploadId, testUrl and the static check report; fix a broken verdict and upload again. When you change a build you already uploaded, add --from <your game's slug or your last uploadId>: files this helper sent before and that haven't changed are copied instead of sent again, so a small change is quick even on a big game. A ROM mod (kind "patch") is its one patch file (.ips, .ups, .bps or .xdelta) and no index.html: pass the file itself to the helper and it is staged as a package with no page to check; a cosmetic's folder is staged with --package (by hand, POST /api/upload/start with package: true beside files). On an "Ideas and test builds only" connection (scope build) the helper works with upload_token's token and stages a private test build; upload_token's reply there gives the steps. On an "Ideas and test builds only" connection the token stages only a private test build (upload-build.mjs with the build folder or its zip, up to 5 GB per build and 512 MB per file), and its reply says how.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "upload_token"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

The description adds substantial behavior beyond the annotations: the token is short-lived, does not reveal the connection's sign-in token, cannot publish, and is subject to concrete upload limits of 5 GB per build, 512 MB per file, and 5,000 files. It also documents the staging helper, streaming endpoints, zip handling, --from reuse behavior, ROM mod packaging, and scope-specific private test builds. Nothing in the description contradicts the supplied annotations.

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

Conciseness2/5

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

The description is heavily overlong for a zero-parameter token-minting tool. Much of the text is procedural documentation for the external helper script, and the final paragraph repeats the earlier 'Ideas and test builds only' scope explanation almost verbatim, which wastes space and buries the core purpose.

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?

It is very complete on operational context, including authentication, limits, staging behavior, and scope variants. However, without an output schema it only indirectly describes what this tool itself returns, and the description conflates the token tool with the upload helper's results and workflow.

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?

The tool takes zero parameters, so there is no parameter semantics for the description to clarify beyond the schema. A baseline of 4 is appropriate because the description does not need to compensate for missing schema coverage.

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 first sentence states a specific verb and resource: it 'mints a short-lived bearer token' for staging builds and media, and it explicitly says the tool cannot publish. That makes the purpose clear, though it does not explicitly distinguish itself from the sibling native_upload_token.

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 clear context for use: staging builds and media, with sign-in required via OAuth or an API key, and it states the important exclusion that the token cannot publish. It also describes scope-specific behavior for 'Ideas and test builds only' connections, but it does not name alternatives or explain when another tool should be used instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources