Agentic AI Foundation

aid: agentic-ai-foundation
name: Agentic AI Foundation
description: 'The Agentic AI Foundation (AAIF) is a Linux Foundation project, announced 9 December 2025, that gives the core
  open standards and projects of the AI agent ecosystem a neutral home. It hosts five projects: Anthropic''s Model Context
  Protocol (MCP), Block''s goose agent, OpenAI''s AGENTS.md, the Agent2Agent (A2A) protocol, and agentgateway. Platinum members
  include Amazon Web Services, Anthropic, Block, Bloomberg, Cloudflare, Google, Microsoft and OpenAI. AAIF publishes no commercial
  API of its own; the callable surface in this profile belongs to its hosted projects — the Official MCP Registry REST API,
  a live anonymous MCP server on the MCP documentation host, and an A2A agent card served from the same host. Eight working
  groups cover reliability, agentic commerce, governance and regulatory alignment, identity and trust, observability, security
  and privacy, workflow integration, and taxonomy.'
url: https://raw.githubusercontent.com/api-evangelist/agentic-ai-foundation/refs/heads/main/apis.yml
humanURL: https://aaif.io/
type: Index
deliveryModel:
  model: unknown
  open_source: unknown
  commercial: false
  callable_host: false
  label: Delivery model not determined — needs a product licence on record
  confidence: low
  source:
  - repository-unlicensed
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Freemium
  confidence: medium
  source:
  - plans
  generated: '2026-07-22'
  method: derived
position: Consuming
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/agentic-ai-foundation.png
tags:
- AI Agents
- Linux Foundation
- Open-Source
- Standards
- MCP
- Agentic AI
- Interoperability
- Agent Protocols
- A2A
- AGENTS.md
- Open Governance
tags_raw:
- AI Agents
- Linux Foundation
- Open Source
- Standards
- MCP
- Agentic AI
- Interoperability
- Agent Protocols
- A2A
- AGENTS.md
- Open Governance
created: '2026-03-16'
modified: '2026-08-30'
specificationVersion: '0.23'
apis:
- aid: agentic-ai-foundation:model-context-protocol
  name: Model Context Protocol (MCP)
  description: The Model Context Protocol (MCP) is an open JSON-RPC 2.0 standard for connecting AI applications to external
    systems — tools, resources and reusable prompt templates. Originally developed by Anthropic and donated to the Agentic
    AI Foundation, it is date-versioned; the current revision is 2026-07-28. The documentation host also operates a live,
    anonymous remote MCP server at /mcp exposing three tools, and serves an A2A agent card and two Agent Skills from /.well-known/.
  humanURL: https://modelcontextprotocol.io/
  tags:
  - MCP
  - Open Standard
  - Tool Use
  - AI Agents
  tags_raw:
  - MCP
  - Model Context Protocol
  - Open Standard
  - Tool Use
  - AI Agents
  properties:
  - type: Documentation
    url: https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro
  - type: GettingStarted
    url: https://modelcontextprotocol.io/docs/2026-07-28/develop/build-server
  - type: GitHubRepository
    url: https://github.com/modelcontextprotocol/modelcontextprotocol
  - type: Roadmap
    url: https://modelcontextprotocol.io/development/roadmap
  - type: JSONSchema
    url: json-schema/agentic-ai-foundation-mcp-protocol-schema.json
  - type: MCPServer
    url: mcp/agentic-ai-foundation-mcp.yml
  - type: AgentCard
    url: a2a/agentic-ai-foundation-a2a.yml
  - type: AgentSkill
    url: skills/_index.yml
  - type: LLMsTxt
    url: https://modelcontextprotocol.io/llms.txt
  baseURL: https://modelcontextprotocol.io/mcp
- aid: agentic-ai-foundation:mcp-registry
  name: Official MCP Registry API
  description: The Official MCP Registry is the community registry service for Model Context Protocol servers, run by the
    MCP project. Its REST API publishes a full OpenAPI 3.1.0 contract with 32 operations across two live version prefixes
    (/v0.1 and /v0). Reads are anonymous — list, search and fetch server records with cursor pagination and an updated_since
    incremental-sync filter; writes require a Registry JWT minted by proving namespace ownership through GitHub OAuth, GitHub
    or generic OIDC, a DNS signature, or an HTTP signature. Errors are RFC 9457 problem details.
  humanURL: https://registry.modelcontextprotocol.io/docs
  baseURL: https://registry.modelcontextprotocol.io
  tags:
  - MCP
  - Registry
  - Server Discovery
  - Open Standard
  - REST API
  tags_raw:
  - MCP
  - Registry
  - Server Discovery
  - Open Standard
  - REST API
  properties:
  - type: OpenAPI
    url: openapi/agentic-ai-foundation-mcp-registry-openapi.yaml
  - type: Overlay
    url: overlays/agentic-ai-foundation-mcp-registry-overlay.yaml
  - type: APIReference
    url: https://registry.modelcontextprotocol.io/docs
  - type: Documentation
    url: https://github.com/modelcontextprotocol/registry/tree/main/docs
  - type: GitHubRepository
    url: https://github.com/modelcontextprotocol/registry
  - type: Authentication
    url: authentication/agentic-ai-foundation-authentication.yml
  - type: ErrorCatalog
    url: errors/agentic-ai-foundation-problem-types.yml
  - type: DataModel
    url: data-model/agentic-ai-foundation-data-model.yml
  - type: Conventions
    url: conventions/agentic-ai-foundation-conventions.yml
  - type: ToolCrosswalk
    url: mcp/agentic-ai-foundation-tool-crosswalk.yml
- aid: agentic-ai-foundation:goose
  name: Goose AI Agent
  description: goose is a general-purpose, open-source AI agent that runs locally. Originally from Block and now governed
    by AAIF, it is written in Rust, ships a desktop app and a CLI for macOS, Linux and Windows, connects to 15+ LLM providers,
    and extends itself through MCP servers. It can also run as an Agent Client Protocol (ACP) agent server over stdio. Current
    release v1.48.0 (2026-08-27).
  humanURL: https://goose-docs.ai/
  tags:
  - AI Agent
  - Open-Source
  - MCP
  - CLI
  - Desktop App
  - Rust
  tags_raw:
  - AI Agent
  - Open Source
  - MCP
  - CLI
  - Desktop App
  - Rust
  properties:
  - type: Documentation
    url: https://goose-docs.ai/
  - type: GettingStarted
    url: https://goose-docs.ai/docs/quickstart/
  - type: GitHubRepository
    url: https://github.com/aaif-goose/goose
  - type: Blog
    url: https://goose-docs.ai/blog/
  - type: CLI
    url: cli/agentic-ai-foundation-cli.yml
  - type: Community
    url: https://discord.com/invite/n8R5VaWDAn
  - type: Releases
    url: https://github.com/aaif-goose/goose/releases
  - type: LLMsTxt
    url: https://goose-docs.ai/llms.txt
- aid: agentic-ai-foundation:agents-md
  name: AGENTS.md
  description: AGENTS.md is a simple, universal convention that gives AI coding agents a consistent, predictable source of
    project-specific guidance — build commands, test commands, conventions and constraints — in one Markdown file at the root
    of a repository. Contributed by OpenAI and hosted by AAIF. It is a format convention rather than a callable API.
  humanURL: https://agents.md/
  tags:
  - AGENTS.md
  - Coding Agents
  - Conventions
  - Open Standard
  tags_raw:
  - AGENTS.md
  - Coding Agents
  - Convention
  - Open Standard
  properties:
  - type: Documentation
    url: https://agents.md/
  - type: GitHubRepository
    url: https://github.com/agentsmd/agents.md
- aid: agentic-ai-foundation:agent2agent
  name: Agent2Agent (A2A)
  description: Agent2Agent (A2A) is an open protocol that lets AI agents built by different organisations, on different frameworks,
    discover each other's capabilities, communicate, delegate tasks and collaborate on multi-step work without sharing internal
    implementations. Discovery happens through an agent card published at /.well-known/agent-card.json. Hosted by AAIF.
  humanURL: https://a2a-protocol.org/latest/
  tags:
  - A2A
  - Agent Interoperability
  - Open Standard
  - Agent Discovery
  properties:
  - type: Documentation
    url: https://a2a-protocol.org/latest/
  - type: GitHubRepository
    url: https://github.com/a2aproject/A2A
  - type: LLMsTxt
    url: https://a2a-protocol.org/llms.txt
- aid: agentic-ai-foundation:agentgateway
  name: agentgateway
  description: agentgateway is an open-source data plane for agentic AI — it secures, observes and governs the connections
    between AI agents, models, MCP tools and APIs across ecosystems. Hosted by AAIF; current release v1.5.0 (2026-08-27).
    It is self-hosted infrastructure rather than a hosted service, so it exposes no public API endpoint of its own.
  humanURL: https://agentgateway.dev/
  tags:
  - Agent Gateway
  - MCP
  - Infrastructure
  - Open-Source
  - Security
  properties:
  - type: Documentation
    url: https://agentgateway.dev/
  - type: GitHubRepository
    url: https://github.com/agentgateway/agentgateway
  - type: Releases
    url: https://github.com/agentgateway/agentgateway/releases
  - type: LLMsTxt
    url: https://agentgateway.dev/llms.txt
common:
- type: Website
  url: https://aaif.io/
- type: Portal
  url: https://aaif.io/
- type: DeveloperPortal
  url: https://aaif.io/projects
- type: Documentation
  url: https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro
- type: APIReference
  url: https://registry.modelcontextprotocol.io/docs
- type: GettingStarted
  url: https://modelcontextprotocol.io/docs/2026-07-28/develop/build-server
- type: Blog
  url: https://aaif.io/blog
- type: News
  url: https://aaif.io/news
- type: Support
  url: https://aaif.io/contact
- type: Community
  url: https://discord.com/invite/n8R5VaWDAn
- type: Roadmap
  url: https://modelcontextprotocol.io/development/roadmap
- type: GitHubOrganization
  url: https://github.com/aaif
- type: IssueTracker
  url: https://github.com/modelcontextprotocol/modelcontextprotocol/issues
- type: Releases
  url: https://github.com/modelcontextprotocol/modelcontextprotocol/releases
- type: SecurityPolicy
  url: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/SECURITY.md
- type: Security
  url: security/agentic-ai-foundation-vulnerability-disclosure.yml
- type: VulnerabilityDisclosure
  url: security/agentic-ai-foundation-vulnerability-disclosure.yml
- type: SecurityTxt
  url: well-known/agentic-ai-foundation-security.txt
- type: WellKnown
  url: well-known/agentic-ai-foundation-well-known.yml
- type: DomainSecurity
  url: security/agentic-ai-foundation-domain-security.yml
- type: CodeOfConduct
  url: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/CODE_OF_CONDUCT.md
- type: ContributionGuide
  url: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/CONTRIBUTING.md
- type: TermsOfService
  url: https://www.linuxfoundation.org/legal/terms
- type: PrivacyPolicy
  url: https://www.linuxfoundation.org/legal/privacy-policy
- type: LinkedIn
  url: https://www.linkedin.com/company/agentic-ai-foundation
- type: MCPServer
  url: mcp/agentic-ai-foundation-mcp.yml
- type: ToolCrosswalk
  url: mcp/agentic-ai-foundation-tool-crosswalk.yml
- type: AgentCard
  url: a2a/agentic-ai-foundation-a2a.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/agentic-ai-foundation-llms.txt
- type: Packages
  url: packages/agentic-ai-foundation-packages.yml
- type: SDKs
  url: packages/agentic-ai-foundation-packages.yml
- type: CLI
  url: cli/agentic-ai-foundation-cli.yml
- type: Authentication
  url: authentication/agentic-ai-foundation-authentication.yml
- type: Conventions
  url: conventions/agentic-ai-foundation-conventions.yml
- type: ErrorCatalog
  url: errors/agentic-ai-foundation-problem-types.yml
- type: DataModel
  url: data-model/agentic-ai-foundation-data-model.yml
- type: Conformance
  url: conformance/agentic-ai-foundation-conformance.yml
- type: Lifecycle
  url: lifecycle/agentic-ai-foundation-lifecycle.yml
- type: ChangeLog
  url: changelog/agentic-ai-foundation-changelog.yml
- type: Overlay
  url: overlays/agentic-ai-foundation-mcp-registry-overlay.yaml
- type: Plans
  url: plans/agentic-ai-foundation-plans-pricing.yml
- type: RateLimits
  url: rate-limits/agentic-ai-foundation-rate-limits.yml
- type: Vocabulary
  url: vocabulary/agentic-ai-foundation-vocabulary.yaml
- type: JSONSchema
  url: json-schema/agentic-ai-foundation-mcp-protocol-schema.json
- type: Examples
  url: examples/agentic-ai-foundation-mcp-tool-example.json
- type: Rules
  url: rules/agentic-ai-foundation-jsonschema-spectral-rules.yml
- type: JSONLD
  url: json-ld/agentic-ai-foundation-context.jsonld
- type: Features
  data:
  - name: Neutral Open Governance
    description: All AAIF projects operate under Linux Foundation neutral governance, ensuring no single vendor controls the
      direction of AI agent standards.
  - name: Model Context Protocol (MCP)
    description: MCP is a universal adapter standard enabling AI agents to connect to any external tool, data source, or workflow
      through a consistent protocol.
  - name: Cross-Platform Agent Portability
    description: AAIF standards enable AI agents to run consistently across different platforms, environments, and LLM providers
      without vendor lock-in.
  - name: Tool and Extension Ecosystem
    description: The MCP standard enables a rich ecosystem of 70+ tools and extensions that any compliant agent can discover
      and invoke.
  - name: Multi-LLM Provider Support
    description: AAIF projects support 15+ LLM providers including Anthropic, OpenAI, Google, Azure, and Ollama through standardized
      provider interfaces.
  - name: Open Agent Communication
    description: The Agent Communication Protocol (ACP) enables agents to authenticate and communicate with each other and
      LLM providers through open standards.
- type: UseCases
  data:
  - name: Interoperable AI Tool Development
    description: Build MCP-compatible tools once and make them available to any AI agent or client that supports the MCP standard,
      eliminating integration silos.
  - name: Enterprise Agent Standardization
    description: Organizations adopt AAIF standards to ensure their AI agent infrastructure is portable, auditable, and not
      locked to a single AI vendor.
  - name: Multi-Agent Workflow Orchestration
    description: Use AAIF protocols to connect specialized AI agents that collaborate on complex tasks, each contributing
      domain-specific capabilities.
  - name: Open-Source Agent Development
    description: Developers build and extend open-source AI agents like goose using the AAIF ecosystem of standards and extensions.
- type: Integrations
  data:
  - name: Claude (Anthropic)
    description: Native MCP support via the Anthropic Messages API, the originating implementation of the MCP standard.
  - name: ChatGPT (OpenAI)
    description: MCP tool integration via the OpenAI Responses API, enabling ChatGPT to invoke MCP-compatible tools.
  - name: VS Code
    description: GitHub Copilot in VS Code supports MCP servers for AI-assisted development through the AAIF MCP standard.
  - name: Cursor
    description: Cursor IDE integrates MCP tool support for AI-assisted coding agents.
  - name: Linux Foundation
    description: AAIF operates under Linux Foundation governance alongside related projects in the LF AI & Data portfolio.
maintainers:
- FN: Kin Lane
  email: info@apievangelist.com
x-enrichment:
  date: '2026-08-30'
  status: enriched
  artifacts_added: 24
  pass: local-v1