agentView

Upload Asset

upload_asset

Upload one or more files (images, fonts, CSS, video, etc.) as assets and receive stable URLs. Use these URLs in your HTML with or @font-face. Assets are cached on displays. Pass files as base64-encoded data. Requires authentication with at least content_only scope.

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": {
      "files": "<files>",
      "descriptions": "<descriptions>"
    },
    "name": "upload_asset"
  }
}

Input Schema

Name	Required	Description
`files`	Yes	Array of file objects, each with 'name' (filename with extension) and 'data' (base64-encoded content).
`group_id`	No	Optional group ID to associate the assets with.
`access_token`	No	Optional bearer token; prefer session_request_id.
`descriptions`	Yes	JSON object mapping each filename to a human-readable description.
`session_request_id`	No	Session handle from create_auth_session; pass it on every authenticated call.

Output Schema

Name	Required	Description	Default
`count`	No
`assets`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 31, 2026

addedInput schema / properties / session_request_id

Added value: +{
+  "description": "Session handle from create_auth_session; pass it on every authenticated call.",
+  "type": "string"
+}

Changed1 schema field changedJul 6, 2026

changedInput schema / properties / access_token / description

Previous value: -"Optional JWT access token for authentication."New value: +"Optional bearer token; prefer session_request_id."

Changed8 schema fields changedJun 2, 2026
- changedOutput schema / properties / assets / items / properties / assetId / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / assets / items / properties / mimeType / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / assets / items / properties / name / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / assets / items / properties / sizeBytes / type
```
Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]
```
- changedOutput schema / properties / assets / items / properties / url / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / assets / items / type
```
Previous value: -"object"New value: +[
+  "object",
+  "null"
+]
```
- changedOutput schema / properties / assets / type
```
Previous value: -"array"New value: +[
+  "array",
+  "null"
+]
```
- changedOutput schema / properties / count / type
```
Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]
```

Changed11 schema fields changedMay 23, 2026

removedInput schema / properties / access_token / default
```
Removed value: -null
```

changedInput schema / properties / access_token / type

Previous value: -[
-  "string",
-  "null"
-]New value: +"string"

changedInput schema / properties / descriptions / description

Previous value: -"JSON object mapping each filename to a human-readable description, e.g. {\"logo.png\": \"Company logo white on transparent\"}. Every file must have an entry."New value: +"JSON object mapping each filename to a human-readable description."

addedInput schema / properties / descriptions / type
```
Added value: +"object"
```

changedInput schema / properties / files / description

Previous value: -"Array of file objects, each with 'name' (filename with extension, e.g. 'logo.png') and 'data' (base64-encoded file content)."New value: +"Array of file objects, each with 'name' (filename with extension) and 'data' (base64-encoded content)."

addedInput schema / properties / files / items

Added value: +{
+  "properties": {
+    "data": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / files / type
```
Added value: +"array"
```
removedInput schema / properties / group_id / default
```
Removed value: -null
```

changedInput schema / properties / group_id / description

Previous value: -"Group/organization ID for shared storage. Pass the display's orgId when uploading assets for an organization display. Omit for personal displays."New value: +"Optional group ID to associate the assets with."

changedInput schema / properties / group_id / type

Previous value: -[
-  "string",
-  "null"
-]New value: +"string"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "assets": {
+      "items": {
+        "properties": {
+          "assetId": {
+            "type": "string"
+          },
+          "mimeType": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "sizeBytes": {
+            "type": "integer"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "count": {
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

First observedMay 8, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond annotations, the description adds meaningful behavioral details: files are base64-encoded, assets are cached on displays, and authentication requires at least content_only scope. It does not contradict annotations and provides useful operational context.

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?

The description is tightly written: purpose, usage context, encoding behavior, and auth requirement each earn their place. It is front-loaded with the core action and avoids redundant filler.

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?

Given the schema and output schema cover structured details, the description is nearly complete: it explains the main use case, encoding requirement, cache behavior, and auth constraints. The required 'descriptions' parameter is not highlighted in prose, but the schema documents it fully.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description reinforces that files are base64-encoded and supports multiple files, but it adds little meaning beyond what the schema already documents for individual parameters.

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?

The description uses a specific verb ('Upload') and resource ('files... as assets') and clearly states the outcome ('receive stable URLs'). It differentiates from sibling tools by framing uploads against delete/get/list/update assets with no ambiguity.

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?

Clear use context is provided: upload files to be referenced in HTML via <img src> or @font-face, with stable URLs and display caching. It does not explicitly name alternatives or say when not to use this tool, but the context is strong enough to guide selection.

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

All agentView 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?