QRStuff MCP Server

Upload file

upload_file

Use this only as a step before generate_qr_code, update_qr_code or submit_batch, when the user has given a file to put behind a code (PDF, image, audio, video) or a logo or background image. Uploads it to the user's QRStuff storage and returns an idfs_file ID. Makes no QR code by itself.

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_file"
  }
}

Input Schema

Name	Required	Description	Default
`file`	No	The file the user attached.
`mime_type`	No	MIME type of the file, for example application/pdf.	application/octet-stream
`base64_data`	No	Base64-encoded file content, for clients that cannot attach files. Send either file or base64_data.

Output Schema

Name	Required	Description	Default
`idfs_file`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 30, 2026

addedInput schema / properties / base64_data / anyOf

Added value: +[
+  {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / base64_data / default
```
Added value: +null
```

changedInput schema / properties / base64_data / description

Previous value: -"Base64-encoded file content"New value: +"Base64-encoded file content, for clients that cannot attach files. Send either file or base64_data."

removedInput schema / properties / base64_data / type
```
Removed value: -"string"
```

addedInput schema / properties / file

Added value: +{
+  "anyOf": [
+    {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "description": "A file the user attached in ChatGPT; the client sends a short-lived URL.",
+          "properties": {
+            "download_url": {
+              "description": "HTTPS link to the file.",
+              "type": "string"
+            },
+            "file_id": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null,
+              "description": "Client file ID."
+            }
+          },
+          "required": [
+            "download_url"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The file the user attached."
+}

addedInput schema / properties / mime_type / default
```
Added value: +"application/octet-stream"
```

changedInput schema / properties / mime_type / description

Previous value: -"MIME type of uploaded file"New value: +"MIME type of the file, for example application/pdf."

removedInput schema / required

Removed value: -[
-  "base64_data",
-  "mime_type"
-]

First observedOct 12, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations declare it is a non-readonly, non-destructive, non-idempotent write; the description adds useful context beyond that by naming the storage destination, the returned `idfs_file` ID, and the fact that no QR code is created. It stops short of noting that repeat uploads are not idempotent or any size/type limits.

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

Conciseness5/5

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

Three sentences, front-loaded with the usage gate, then the action, then the negative scope. No filler or restatement of the title.

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?

An output schema exists, yet the description still surfaces the key return value (`idfs_file` ID) that downstream calls need. Combined with the explicit sequencing guidance, an agent has everything required to invoke this 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 100%, so the baseline is 3, but the description adds real meaning by enumerating the acceptable file categories (PDF, image, audio, video, logo, background image) that the schema does not express. It says nothing extra about `mime_type` or the `base64_data` alternative.

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 (uploads a file to the user's QRStuff storage) plus the concrete output (an `idfs_file` ID). The closing line 'Makes no QR code by itself' sharply distinguishes it from the many generate_*/create_* siblings.

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 precondition ('only as a step before generate_qr_code, update_qr_code or submit_batch') and the triggering situation ('when the user has given a file'). It also names the three concrete follow-up tools, leaving nothing to inference about sequencing.

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

All QRStuff MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?