---
schema_version: "newruntime-topic-hub-v0.2"
type: "topic_hub"
stable_id: "topic_hub:agent-protocols"
slug: "agent-protocols"
title: "Agent Protocols - New Runtime"
description: "A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent protocols."
retrieval_nugget: "A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent protocols. Agent Protocols is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records."
answer: ["Agent Protocols is tracked here as an evidence-linked topic, not as a static glossary entry.","The page connects raw observations to pattern hypotheses, longer analysis, and public sources.","Use it as the canonical landing page before drilling into individual records."]
search_intents: ["agent protocols","agent protocols AI agents","agent protocols software"]
status: "featured"
last_updated: "2026-07-29"
record_date: "2026-07-29"
date_kind: "last_updated"
counts: {"total":98,"signals":96,"patterns":1,"posts":1,"atlas":0,"sources":156}
routes: {"html":"https://newruntime.com/topics/agent-protocols/","markdown":"https://newruntime.com/topics/agent-protocols.md","json":"https://newruntime.com/topics/agent-protocols.json"}
source_urls: ["https://addyosmani.com/blog/good-spec","https://agentation.com/","https://agentation.dev/","https://agenticcommerce.dev/","https://agenticcommerce.dev/llms.txt","https://ai.google.dev/gemini-api/docs/interactions?ua=chat","https://anthropic.com/engineering/claude-code-sandboxing","https://anthropic.com/engineering/code-execution-with-mcp","https://anthropic.com/engineering/effective-harnesses-for-long-running-agents","https://anthropic.com/news/claude-code-on-the-web","https://anthropic.com/news/claude-code-plugins","https://anthropic.com/news/claude-sonnet-4-6"]
top_sources: ["https://addyosmani.com/blog/good-spec","https://agentation.com/","https://agentation.dev/","https://agenticcommerce.dev/","https://agenticcommerce.dev/llms.txt","https://ai.google.dev/gemini-api/docs/interactions?ua=chat","https://anthropic.com/engineering/claude-code-sandboxing","https://anthropic.com/engineering/code-execution-with-mcp","https://anthropic.com/engineering/effective-harnesses-for-long-running-agents","https://anthropic.com/news/claude-code-on-the-web","https://anthropic.com/news/claude-code-plugins","https://anthropic.com/news/claude-sonnet-4-6"]
---

# Agent Protocols - New Runtime

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent protocols.

## Retrieval answer

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent protocols. Agent Protocols is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records.

## Patterns

- [Agent protocols become the interoperability layer](https://newruntime.com/patterns/agent-protocols-become-interoperability-layer/): The durable integration surface for agentic software is becoming a small family of protocols that separate models and harnesses from tools, services, interfaces, and other agents.

## Field Notes

- [MCP and OAuth Put Agent Authorization on the Critical Path](https://newruntime.com/posts/mcp-oauth-authorization-boundary/): PropelAuth's MCP and OAuth 2.1 deep dive shows that agent protocols need explicit user, client, server, and scope boundaries.

## Recent Raw Signals

- 2026-07-29: [MCP and OAuth Put Agent Authorization on the Critical Path](https://newruntime.com/signals/mcp-oauth-authorization-boundary/)
- 2026-05-22: [GitHub / yichuan-w/LEANN: Routable Model Components](https://newruntime.com/signals/github-yichuan-w-leann-routable-model-components/)
- 2026-04-29: [GitHub / openai/realtime-voice-component: Agent-Ready Software](https://newruntime.com/signals/github-openai-realtime-voice-component-agent-ready-software/)
- 2026-04-26: [GitHub / zapier/AutomationBench: Verification Bandwidth](https://newruntime.com/signals/github-zapier-automationbench-verification-bandwidth/)
- 2026-04-23: [OpenAI / Workspace Agents: Ai-Native Operating Models](https://newruntime.com/signals/openai-workspace-agents-ai-native-operating-models/)
- 2026-04-21: [Venturebeat / Salesforce Launches Headless To Turn Its Entire: Agent Protocol Interoperability](https://newruntime.com/signals/venturebeat-salesforce-launches-headless-to-turn-its-entire-agent-protocol-interoperability/)
- 2026-04-16: [OpenAI / Next Evolution Of Agents Sdk: Agent-Ready Software](https://newruntime.com/signals/openai-next-evolution-of-agents-sdk-agent-ready-software/)
- 2026-04-12: [GitHub / langchain-ai/deepagents: Agent-Ready Software](https://newruntime.com/signals/github-langchain-ai-deepagents-agent-ready-software-2003/)
- 2026-04-05: [Agentation: Task-Specific Ai Interfaces](https://newruntime.com/signals/agentation-task-specific-ai-interfaces/)
- 2026-04-05: [GitHub / jgraph/drawio-mcp: Executable Design Context](https://newruntime.com/signals/github-jgraph-drawio-mcp-executable-design-context/)
- 2026-03-26: [Chrlschn / Mcp Is Dead Long Live Mcp: Agent Protocol Interoperability](https://newruntime.com/signals/chrlschn-mcp-is-dead-long-live-mcp-agent-protocol-interoperability/)
- 2026-03-23: [Cursor: Agent-Ready Software](https://newruntime.com/signals/cursor-agent-ready-software-1682/)
- 2026-03-20: [GitHub / Agent-Field/agentfield: Agent-Ready Software](https://newruntime.com/signals/github-agent-field-agentfield-agent-ready-software/)
- 2026-03-20: [OpenAI / Gpt Mini Nano: Ai-Native Operating Models](https://newruntime.com/signals/openai-gpt-mini-nano-ai-native-operating-models/)
- 2026-03-18: [GitHub / msitarzewski/agency-agents: Verification Bandwidth](https://newruntime.com/signals/github-msitarzewski-agency-agents-verification-bandwidth/)
- 2026-02-28: [Google AI / Gemini Api: Agent Protocol Interoperability](https://newruntime.com/signals/google-ai-gemini-api-agent-protocol-interoperability/)

## Public Sources

- https://addyosmani.com/blog/good-spec
- https://agentation.com/
- https://agentation.dev/
- https://agenticcommerce.dev/
- https://agenticcommerce.dev/llms.txt
- https://ai.google.dev/gemini-api/docs/interactions?ua=chat
- https://anthropic.com/engineering/claude-code-sandboxing
- https://anthropic.com/engineering/code-execution-with-mcp
- https://anthropic.com/engineering/effective-harnesses-for-long-running-agents
- https://anthropic.com/news/claude-code-on-the-web
- https://anthropic.com/news/claude-code-plugins
- https://anthropic.com/news/claude-sonnet-4-6