Agent Manifest
Structure and usage of the Agent Manifest
The Agent Manifest describes essential properties of an agent, including its identity, capabilities, metadata, and runtime status. It also plays an important role in discoverability and how the ACP server advertises agents to clients.Documentation Index
Fetch the complete documentation index at: https://agentcommunicationprotocol.dev/llms.txt
Use this file to discover all available pages before exploring further.
Example SDK Implementation
The@server.agent decorator is used to configure an agent’s metadata when registering it with an ACP server:
Parameters
Content Types
Theinput_content_types and output_content_types fields specify the MIME types that an agent can handle. Wildcards are supported.
Common Content Types
*/*: Any contentimage/*: Any imagetext/plain: Plain text contentapplication/json: JSON structured dataimage/png: PNG image filesimage/jpeg: JPEG image filesapplication/pdf: PDF documents
Example Usage
Default Values
Ifinput_content_types and output_content_types are not specified in the decorator, they default to ["*/*"]:
A unique identifier for the agent following the RFC 1123 DNS label naming convention.
1 - 63^[a-z0-9]([-a-z0-9]*[a-z0-9])?$"chat"
Human-readable description of the agent.
"Conversational agent with memory, supporting real-time search, Wikipedia lookups, and weather updates through integrated tools"
List of supported MIME content types for input Messages. Defines what formats of content the agent can consume.
1List of supported MIME content types for output Messages. Defines what formats of content the agent can produce.
1Static details about the agent, for discovery, classification, and cataloging.
Real-time dynamic metrics and state provided by the system managing the agent.