Skip to main content
Glama

Kubeez

get_upload_url

Scope: generate:media. PRE-FETCH (mandatory): resources/read kubeez://skills/media-upload — explains the full flow, what the response contains, and how duration_seconds powers exact billing.

Create a temporary upload session that returns BOTH a browser link (for a human user) AND a direct upload endpoint the agent POSTs to itself from its own environment (shell, code execution sandbox, Claude Code, Cursor). REQUIRED whenever the user wants to supply a photo / video / audio file to edit, animate, reference, lip-sync, or stem-separate but does not already have a stable public HTTPS URL. Pass model_id from get_models for the generation you plan (enforces max_input_images and input_media_types). Response fields: • url — browser link the user opens to upload (no Kubeez login). • direct_upload_url + direct_upload_curl_example — POST endpoint for AI agents that already have the file on disk. Multipart form: token + one or MORE file parts (repeat -F "file=@..." to batch several files in one curl). Same token as the browser link; both write to the same session. • direct_upload_python_example — the same upload with Python requests, for sandboxes without curl. • direct_upload_allowlist_domains — the one domain the upload needs (a kubeez.com host). If your sandbox blocks the request (DNS failure, connection refused, proxy 403), ask the user to allow it in the sandbox's network settings, or try direct_upload_fallback_url. • token — pass to get_upload_session afterwards. If you (the agent) already have the file in your environment, upload it yourself with the direct endpoint — no need to round-trip the user. If the file is on the user's device only, share url and ask them to upload there. After upload(s), call get_upload_session(token) to retrieve media_urls, then pass those as source_media_urls to generate_media.

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": {
      "model_id": "<model_id>"
    },
    "name": "get_upload_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds the session semantics that matter — both endpoints write to the same token-scoped session, `token` is carried to get_upload_session, and a kubeez.com domain is allowlisted with fallback advice for sandboxes that block it. It also names the required scope (generate:media) and a mandatory pre-fetch resource read.

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 scope and the mandatory pre-fetch, then the one-paragraph purpose, then a bulleted field reference that maps each return field to the action to take. It is long, and the response-field bullets partly restate what the existing output schema already carries, but the fields are annotated with usage rather than just named.

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?

Complete for a multi-step flow tool that sits between model selection and generation: it covers the prerequisite resource read, the required parameter source, both upload paths, sandbox failure remediation, and the exact next call. With an output schema present, it does not need to restate return values, and its field notes are usage-oriented rather than duplicative.

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 0% for the single `model_id` parameter, so the description must carry the load — and it does: it says where the value comes from (get_models for the intended generation) and what it controls (enforcing max_input_images and input_media_types). It stops short of format details or what happens if the model doesn't support the intended media type, but the meaning is substantially enhanced.

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 and resource — 'Create a temporary upload session' — and immediately specifies the dual output (browser link for humans, direct endpoint for agents). This distinguishes it cleanly from the sibling get_upload_session, which retrieves results after an upload.

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?

Gives an explicit trigger ('REQUIRED whenever the user wants to supply a photo / video / audio file... but does not already have a stable public HTTPS URL') plus the exclusion (skip it if a public HTTPS URL already exists). It also routes between paths: agent-uploads-itself if the file is local, share `url` if the file is on the user's device, then get_upload_session followed by generate_media.

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