Everything in the catalog

Open protocol for agents built on different frameworks and vendors to discover each other and collaborate on tasks.

Event-based protocol that streams agent state, messages and tool calls between an agent backend and a user-facing app.

Open JSON-RPC protocol that lets AI applications connect to external tools, data sources and prompts through MCP servers.

Open folder format (a SKILL.md plus optional scripts and files) for packaging instructions an agent loads on demand.

Official open catalog and API for publicly available MCP servers, run by the MCP project.

Open payment standard that uses the HTTP 402 status code so clients, including agents, can pay per request.

Plain Markdown file at a repository root that tells coding agents how to build, test and work in the project.

JSON-RPC protocol that lets any code editor run any coding agent, locally over stdio or remotely over HTTP.

Open standard for agentic commerce covering discovery, checkout and post-purchase between platforms, agents and businesses.

Revised version of OSWorld, a benchmark of open-ended tasks on real desktop operating systems for computer-use agents.

Official MCP extension that lets tools return interactive HTML interfaces rendered in a sandboxed iframe inside the chat.

Human-validated set of 500 real GitHub issues from Python repositories for testing coding agents.

Simulated customer-service benchmark where an agent follows domain policies and uses tools while a simulated user also acts.

Benchmark of hard, realistic command-line tasks that agents must complete inside a terminal sandbox.

Proposal for a Markdown /llms.txt file that gives language models a short, curated map of a website's content.

Benchmark and framework that tests models and agents on tasks using real-world MCP servers.

2,500 expert-written, closed-ended questions across dozens of academic subjects, including multimodal items.

OpenTelemetry attribute names and signal shapes for tracing LLM calls, agents, tool execution and MCP operations.

Interactive benchmark of novel game-like environments that agents must explore and learn without instructions.

Benchmark of 450+ real-world questions for general AI assistants, split into three difficulty levels.

Leaderboard that tests how accurately models call functions and tools, from single calls to multi-turn agentic use.

Open protocol for agent-initiated payments, built as an extension to A2A and MCP, with signed user mandates.

Set of 108 long-horizon computer-use workflows covering everyday and professional desktop work.

Framework-neutral configuration language for describing agents and flows so they can be serialized and run on different runtimes.