Content

A content block is one piece of user-facing content: text, an image, audio, a link to a resource, or an embedded resource. Content blocks appear in:

User prompts sent via session/prompt
Language model output streamed through session/update notifications
Progress updates and results from tool calls

Content types

Content from the Agent is untrusted. See Rendering Agent Content and URIs and Remote Resources. ACP’s ContentBlock is compatible with, and a superset of, the Model Context Protocol (MCP) 2025-06-18 ContentBlock, so Agents can forward content from MCP tool outputs unchanged. ACP adds an optional uri on image content.

Text content

Text may be plain text or Markdown. Clients SHOULD render it as Markdown. See Rendering Agent Content for raw HTML.

{
  "type": "text",
  "text": "What's the weather like today?"
}

All Agents MUST support text content blocks when included in prompts.

string

required

The text content to display

Annotations

Optional metadata about how the content should be used or displayed. Learn more.

Image content

Images can be included for visual context or analysis.

{
  "type": "image",
  "mimeType": "image/png",
  "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAAB..."
}

Requires the image prompt capability when included in prompts.

string

required

Base64-encoded image data

string

required

The MIME type of the image (e.g., “image/png”, “image/jpeg”)

string

Optional URI reference for the image source

Annotations

Optional metadata about how the content should be used or displayed. Learn more.

Audio content

Audio data for transcription or analysis.

{
  "type": "audio",
  "mimeType": "audio/wav",
  "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAAB..."
}

Requires the audio prompt capability when included in prompts.

string

required

Base64-encoded audio data

string

required

The MIME type of the audio (e.g., “audio/wav”, “audio/mp3”)

Annotations

Optional metadata about how the content should be used or displayed. Learn more.

Embedded resource

Complete resource contents embedded directly in the message.

{
  "type": "resource",
  "resource": {
    "uri": "file:///home/user/script.py",
    "mimeType": "text/x-python",
    "text": "def hello():\n    print('Hello, world!')"
  }
}

This is the preferred way to include context in prompts, such as when using @-mentions to reference files or other resources. By embedding the content directly in the request, Clients can include context from sources that the Agent may not have direct access to. Requires the embeddedContext prompt capability when included in prompts.

EmbeddedResourceResource

required

The embedded resource contents, which can be either:

Show Text Resource

string

required

The URI identifying the resource

string

required

The text content of the resource

string

Optional MIME type of the text content

Show Blob Resource

string

required

The URI identifying the resource

string

required

Base64-encoded binary data

string

Optional MIME type of the blob

Annotations

Optional metadata about how the content should be used or displayed. Learn more.

Resource link

References to resources that the Agent can access. All Agents MUST support resource links when included in prompts.

{
  "type": "resource_link",
  "uri": "file:///home/user/document.pdf",
  "name": "document.pdf",
  "mimeType": "application/pdf",
  "size": 1024000
}

string

required

The URI of the resource

string

required

A human-readable name for the resource

string

The MIME type of the resource

string

Optional display title for the resource

string

Optional description of the resource contents

integer

Optional size of the resource in bytes

Annotations

Optional metadata about how the content should be used or displayed. Learn more.

Get Started

Protocol

Libraries

Content types

Text content

Image content

Audio content

Embedded resource

Resource link