Skip to main content
Glama

Import media from a URL

import_media

Fetch a file the client cannot upload itself and store it as an account upload. When the user attaches a picture, clip or sound in ChatGPT, pass it as file; otherwise pass url. The result's reference goes into any generate tool. A file with no URL this server can reach (a claude.ai attachment) needs request_upload_link instead. Only these hosts are fetched: files.oaiusercontent.com.

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": "import_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
fileNo
filenameNo
mime_typeNo

Output Schema

NameRequiredDescriptionDefault
uploadYesA file you brought into Kuro.
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changed
    • addedOutput schema / properties / upload / description
      Added value: +"A file you brought into Kuro."
    • changedOutput schema / properties / upload / properties / bytes / type
      Previous value: -"number"New value: +"integer"
    • addedOutput schema / properties / upload / properties / created_at
      Added value: +{
      +  "format": "date-time",
      +  "type": "string"
      +}
    • addedOutput schema / properties / upload / properties / id
      Added value: +{
      +  "format": "uuid",
      +  "type": "string"
      +}
    • removedOutput schema / properties / upload / properties / kind
      Removed value: -{
      -  "enum": [
      -    "image",
      -    "audio",
      -    "video"
      -  ],
      -  "type": "string"
      -}
    • addedOutput schema / properties / upload / properties / object
      Added value: +{
      +  "const": "upload",
      +  "type": "string"
      +}
    • changedOutput schema / properties / upload / properties / reference / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "type": {
      -        "const": "upload",
      -        "type": "string"
      -      },
      -      "upload_id": {
      -        "format": "uuid",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "type",
      -      "upload_id"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "generation_id": {
      -        "format": "uuid",
      -        "type": "string"
      -      },
      -      "type": {
      -        "const": "generation",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "type",
      -      "generation_id"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "type": {
      +        "const": "upload",
      +        "type": "string"
      +      },
      +      "upload_id": {
      +        "$ref": "#/properties/upload/properties/id"
      +      }
      +    },
      +    "required": [
      +      "type",
      +      "upload_id"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "generation_id": {
      +        "$ref": "#/properties/upload/properties/id"
      +      },
      +      "type": {
      +        "const": "generation",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "type",
      +      "generation_id"
      +    ],
      +    "type": "object"
      +  }
      +]
    • addedOutput schema / properties / upload / properties / reference / description
      Added value: +"Pass this where a request takes media."
    • addedOutput schema / properties / upload / properties / status / description
      Added value: +"Only a `verified` upload can be used in a generation."
    • addedOutput schema / properties / upload / properties / status / enum
      Added value: +[
      +  "pending",
      +  "verified",
      +  "rejected",
      +  "expired"
      +]
    • addedOutput schema / properties / upload / properties / type
      Added value: +{
      +  "enum": [
      +    "image",
      +    "video",
      +    "audio"
      +  ],
      +  "type": "string"
      +}
    • removedOutput schema / properties / upload / properties / upload_id
      Removed value: -{
      -  "format": "uuid",
      -  "type": "string"
      -}
    • addedOutput schema / properties / upload / properties / url / description
      Added value: +"A signed link to the file, for about an hour."
    • changedOutput schema / properties / upload / required
      Previous value: -[
      -  "upload_id",
      -  "filename",
      -  "kind",
      -  "mime_type",
      -  "bytes",
      -  "status",
      -  "url",
      -  "thumbnail_url",
      -  "reference"
      -]New value: +[
      +  "object",
      +  "id",
      +  "filename",
      +  "type",
      +  "mime_type",
      +  "bytes",
      +  "status",
      +  "url",
      +  "thumbnail_url",
      +  "reference",
      +  "created_at"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / file / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "download_url": {
      -        "format": "uri",
      -        "type": "string"
      -      },
      -      "file_id": {
      -        "maxLength": 200,
      -        "type": "string"
      -      },
      -      "file_name": {
      -        "maxLength": 220,
      -        "type": "string"
      -      },
      -      "mime_type": {
      -        "maxLength": 120,
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "download_url"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "maxLength": 2000,
      -    "type": "string"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "download_url": {
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "file_id": {
      +        "maxLength": 200,
      +        "type": "string"
      +      },
      +      "file_name": {
      +        "maxLength": 220,
      +        "type": "string"
      +      },
      +      "mime_type": {
      +        "maxLength": 120,
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "download_url",
      +      "file_id"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "maxLength": 2000,
      +    "type": "string"
      +  }
      +]
  3. Changed2 schema fields changed
    • addedOutput schema / properties / upload / properties / thumbnail_url
      Added value: +{
      +  "anyOf": [
      +    {
      +      "format": "uri",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
    • changedOutput schema / properties / upload / required
      Previous value: -[
      -  "upload_id",
      -  "filename",
      -  "kind",
      -  "mime_type",
      -  "bytes",
      -  "status",
      -  "url",
      -  "reference"
      -]New value: +[
      +  "upload_id",
      +  "filename",
      +  "kind",
      +  "mime_type",
      +  "bytes",
      +  "status",
      +  "url",
      +  "thumbnail_url",
      +  "reference"
      +]
  4. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations, it discloses persistence as an account upload, server-side fetching restricted to files.oaiusercontent.com, and the unreachable-URL case requiring another tool. These details establish concrete storage and network expectations rather than merely repeating the safety hints.

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 front-loads the purpose, then compactly covers input selection, downstream usage, fallback behavior, and the fetch restriction. Every sentence provides operational information without filler.

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?

For this four-parameter import tool, it covers the invocation decision, attachment and URL paths, output handoff, unreachable-file alternative, and sole supported host. The output schema can provide the result structure, so the absence of a field-by-field return explanation is not a gap.

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?

With 0% schema description coverage, the `file`-versus-`url` routing adds essential meaning to the two primary parameters. The optional `filename` and `mime_type` parameters receive no guidance, so the description compensates strongly but not completely for the undocumented schema.

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 opening sentence states a specific action and outcome: fetch a file the client cannot upload and store it as an account upload. It also distinguishes the tool's role from request_upload_link and downstream generate tools.

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 explicitly routes ChatGPT attachments to `file` and other inputs to `url`, while directing unreachable attachments to request_upload_link. The `reference` handoff and host allowlist further clarify how and when the tool can be used successfully.

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