Skip to main content
Glama

Authorize a local reference upload

upload_reference
Idempotent

Get a free, short-lived upload grant for one local file using the existing APIXO MCP login. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Fetch the APIXO uploader from https://mcp.apixo.ai/tools/apixo-upload-reference.v1.mjs and save it locally as apixo-upload-reference.v1.mjs. Run node apixo-upload-reference.v1.mjs inspect with Node.js 22 or later to get the four tool arguments without sending the file. Pass the returned upload_id and grant as JSON on standard input to node apixo-upload-reference.v1.mjs upload . Keep the grant out of user-facing replies and the uploader's command-line arguments. Use the helper's confirmed url for generation. Upload links are public until temporary storage cleanup. If any required upload fails, stop before paid generation and report the issue.

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": {
      "file_name": "<file_name>",
      "content_type": "<content_type>",
      "size_bytes": "<size_bytes>",
      "request_id": "<request_id>"
    },
    "name": "upload_reference"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_nameYes
request_idYesUse the same UUID for retries of this file and its original metadata.
size_bytesYes
content_typeYes

Output Schema

NameRequiredDescriptionDefault
grantYes
upload_idYes
helper_urlYes
upload_urlYes
grant_expires_atYes

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?

Beyond the annotations, it discloses grant lifetime (free, short-lived), that upload links stay public until temporary storage cleanup, that grants must never appear in replies or command-line arguments, and that a failed upload must halt before paid generation. These are security- and side-effect-relevant facts the schema and annotations do not convey. Nothing here contradicts readOnlyHint=false, idempotentHint=true, or destructiveHint=false.

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

Conciseness3/5

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

Purpose and route selection are front-loaded, but the bulk reads like an integration runbook: download a specific .mjs URL, run two exact shell commands, and manage stdin JSON. Much of this arguably belongs in the sibling get_integration_guide tool, and workflow policy ('stop before paid generation') crowds out argument documentation.

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 grant-issuing step in a larger generation pipeline, the description covers the routing decision, the two-phase inspect/upload procedure, secrecy constraints, link visibility, and failure handling, and an output schema means return values need no explanation. The remaining hole is that the four required inputs are left to the schema patterns alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% - just request_id is documented - and the description never explains file_name, content_type, or size_bytes at all, nor the 200 MB ceiling. Its only indirect gesture is 'get the four tool arguments' from the inspect step, which does not define any field's meaning. The description does not compensate for the coverage gap, so it falls below the baseline.

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 gives a concrete verb and resource: obtain a free, short-lived upload grant for one local file, tied to the existing MCP login. It also distinguishes itself from the native-attachment route handled by reference_files. The purpose is clear, though it is buried under a long procedural runbook that dilutes the signal.

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?

It states explicit routing rules: use reference_files when the client provides native APIXO attachments, otherwise use upload_reference when the client can run Node.js 22+ and reach APIXO, with named example clients. It also covers the fallback when execution or file access is unavailable (ask for a direct link), which is exactly the when-not guidance an agent needs.

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