> ## Documentation Index > Fetch the complete documentation index at: https://agentcommunicationprotocol.dev/llms.txt > Use this file to discover all available pages before exploring further. # Agent Manifest > Returns a manifest of the specified agent. ## OpenAPI ````yaml GET /agents/{name} openapi: 3.1.1 info: title: ACP - Agent Communication Protocol description: >- The Agent Communication Protocol (ACP) provides a standardized RESTful API for managing, orchestrating, and executing AI agents. It supports synchronous, asynchronous, and streamed agent interactions, with both stateless and stateful execution modes. license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0.html version: 0.2.0 servers: - url: http://localhost:8000 security: [] tags: - name: agent description: >- Operations for listing, describing, and managing agent definitions and metadata. - name: run description: >- Operations for creating, managing, controlling, and monitoring agent runs and their lifecycles. externalDocs: description: Comprehensive documentation for ACP url: https://agentcommunicationprotocol.dev paths: /agents/{name}: get: tags: - agent summary: Agent Manifest description: Returns a manifest of the specified agent. operationId: getAgent parameters: - name: name in: path required: true description: The name of the agent to retrieve. schema: $ref: '#/components/schemas/AgentName' responses: '200': description: Agent manifests content: application/json: schema: $ref: '#/components/schemas/AgentManifest' default: $ref: '#/components/responses/Error' components: schemas: AgentName: type: string pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ minLength: 1 maxLength: 63 description: >- A unique identifier for the agent following the RFC 1123 DNS label naming convention. example: chat AgentManifest: type: object properties: name: $ref: '#/components/schemas/AgentName' description: type: string description: Human-readable description of the agent. example: >- Conversational agent with memory, supporting real-time search, Wikipedia lookups, and weather updates through integrated tools input_content_types: type: array minItems: 1 description: > List of supported MIME content types for input Messages. Defines what formats of content the agent can consume. items: type: string examples: - '*/*' - image/* - text/plain - application/json - image/png output_content_types: type: array minItems: 1 description: > List of supported MIME content types for output Messages. Defines what formats of content the agent can produce. items: type: string examples: - '*/*' - image/* - text/plain - application/json - image/png metadata: $ref: '#/components/schemas/Metadata' status: $ref: '#/components/schemas/Status' required: - name - description - input_content_types - output_content_types Metadata: type: object properties: annotations: type: object additionalProperties: true description: Key-value annotation metadata. documentation: type: string description: Full agent documentation in markdown. example: >- The agent is a conversational system designed to process user messages, maintain context, and generate... license: type: string description: SPDX license ID. example: Apache-2.0 programming_language: type: string description: Programming language (per GitHub language support). example: Python natural_languages: type: array description: Supported human languages (ISO 639-1 codes). items: type: string example: en framework: type: string description: Agent framework, e.g. BeeAI, crewAI, Autogen, AG2. example: BeeAI capabilities: type: array description: > A structured list describing capabilities supported by the agent. Each capability includes a human-readable name and a brief description. This information might be consumed and interpreted by large language models (LLMs). items: type: object properties: name: type: string description: Human-readable name of the capability. example: Conversational AI description: type: string description: Brief description of what the capability provides or enables. example: Handles multi-turn conversations with memory. required: - name - description example: - name: Conversational AI description: Handles multi-turn conversations with memory. - name: Vacation Request description: Handles submission and tracking of vacation requests. domains: type: array description: > Domains or functional areas applicable to the agent, such as 'finance', 'healthcare', 'supply-chain', or custom-defined domains relevant to your organization or team. items: type: string example: - finance - healthcare - supply-chain tags: type: array items: $ref: '#/components/schemas/Tag' created_at: $ref: '#/components/schemas/Timestamp' updated_at: $ref: '#/components/schemas/Timestamp' author: $ref: '#/components/schemas/Person' contributors: type: array items: $ref: '#/components/schemas/Person' links: type: array items: $ref: '#/components/schemas/Link' example: - type: source-code url: https://github.com/i-am-bee/beeai-platform.git - type: homepage url: https://agentcommunicationprotocol.dev dependencies: type: array items: $ref: '#/components/schemas/AgentDependency' recommended_models: type: array items: type: string description: >- List of recommended model names (see providers such as Ollama, OpenAI, etc.). example: - llama3.3:70b-instruct-fp16 - llama3.3 description: >- Static details about the agent, for discovery, classification, and cataloging. Status: type: object properties: avg_run_tokens: type: number minimum: 0 avg_run_time_seconds: type: number format: float minimum: 0 success_rate: type: number minimum: 0 maximum: 100 description: Percentage of successful runs (0-100). description: >- Real-time dynamic metrics and state provided by the system managing the agent. Error: type: object properties: code: type: string enum: - server_error - invalid_input - not_found message: type: string data: type: object nullable: true required: - code - message Tag: anyOf: - type: string - type: string enum: - Chat - RAG - Canvas - Code - Researcher - Orchestrator example: Chat description: Simple tag or enum for classifying agents. Timestamp: type: string format: date-time description: Timestamp in RFC3339/ISO8601 format. Person: type: object properties: name: type: string example: John Smith email: type: string format: email example: jsmith@example.com url: type: string format: uri example: https://example.com required: - name Link: type: object properties: type: type: string enum: - source-code - container-image - homepage - documentation url: type: string format: uri required: - type - url AgentDependency: type: object description: > **Experimental:** Represents a dependency required by the agent, specifying external resources or capabilities it relies upon, such as other agents, tools, or AI models. properties: type: type: string enum: - agent - tool - model description: > Type of dependency: - `agent`: Another agent instance required to fulfill certain functionalities. - `tool`: External tool or utility needed by the agent. - `model`: Specific AI model that the agent depends on. example: tool name: type: string description: > Identifier or name of the dependency, such as an agent name, tool identifier, or model name. example: weather responses: Error: description: Error response content: application/json: schema: $ref: '#/components/schemas/Error' ````