Agent Action Protocol (AAP) – MCP got us started, but is insufficient
Background: I've been working on agentic guardrails because agents act in expensive/terrible ways and something needs to be able to say "Maybe don't do that" to the agents, but guardrails are almost impossible to enforce with the current way things are built. Context: We keep running into so many problems/limitations today with MCP. It was created so that agents have context on how to act in the world, it wasn't designed to become THE standard rails for agentic behavior. We keep tacking things on to it trying to improve it, but it needs to die a SOAP death so REST can rise in it's…
Agent Action Protocol (AAP) – MCP got us started, but is insufficient launched on March 3, 2026 with 13 votes, #1,024 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
Agent Action Protocol (AAP) is a framework designed to enforce guardrails on AI agents by establishing safety checks before they take actions. Built as an alternative to Model Context Protocol, AAP aims to provide a standardized way to validate and control agent behavior across different systems and prevent expensive or harmful actions. The project addresses limitations in current approaches by proposing a dedicated protocol specifically for action governance rather than retrofitting existing tools.
written from the facts on this page · September 2026
From the sources
AAP: Agent Action Protocol — a portable, composable spec for AI agents taking action in the world - agentactionprotocol/aap
AI agents are taking real actions — creating tickets, sending emails, deploying code, moving money. Every week the scope of what agents can do gets wider and the stakes get higher. MCP was a significant step forward. It standardized how agents discover and call tools — the transport layer. But transport is only one piece of the puzzle. MCP doesn't define what an action is , how actions compose into pipelines, how they're authorized, how they checkpoint and resume, how they roll back when things go wrong, or how they're observed across runtimes. The industry is stretching MCP beyond its design because nothing better exists for the layers above it. This isn't a criticism of MCP — it's an…from github.com
In the maker’s words, at launch
Background: I've been working on agentic guardrails because agents act in expensive/terrible ways and something needs to be able to say "Maybe don't do that" to the agents, but guardrails are almost impossible to enforce with the current way things are built. Context: We keep running into so many…
Does a similar job
all alternatives →
Mcp-Agent – Build effective agents with Model Context Protocol2025 · github.com · ▲80Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](https://github.com/lastmile-ai/mcp-agent) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions. For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and…
Representing Agents as MCP Servers2025 · github.com · ▲58Hey HN! A few months ago we shared mcp-agent (https://github.com/lastmile-ai/mcp-agent) [1][2], a lightweight framework that implements every agent pattern from Anthropic’s Building Effective Agents blog [3] and handles MCP server/client management seamlessly. Our core bet is that connecting LLMs to tools, resources, and external systems will soon be MCP-native by default. Today we're launching a significant update: Agents as MCP servers. Currently "agentic" behavior exists only on the MCP client side – clients like Claude or Cursor use MCP servers to solve tasks.…
Open-source browser for AI agentsMar 2026 · github.com · ▲155Hi HN, I forked chromium and built agent-browser-protocol (ABP) after noticing that most browser-agent failures aren’t really about the model misunderstanding the page. Instead, the problem is that the model is reasoning from a stale state. ABP is designed to keep the acting agent synchronized with the browser at every step. After each action (click, type, etc), it freezes JavaScript execution and rendering, then captures the resulting state. It also compiles the notable events that occurred during that action loop, such as navigation, file pickers, permission prompts, alerts, and downloads,…
Trust Protocols for Anthropic/OpenAI/GeminiFeb 2026 · mnemom.ai · ▲40Much of my work right now involves complex, long-running, multi-agentic teams of agents. I kept running into the same problem: “How do I keep these guys in line?” Rules weren’t cutting it, and we needed a scalable, agentic-native STANDARD I could count on. There wasn’t one. So I built one. Here are two open-source protocols that extend A2A, granting AI agents behavioral contracts and runtime integrity monitoring: - Agent Alignment Protocol (AAP): What an agent can do / has done. - Agent Integrity Protocol (AIP): What an agent is thinking about doing / is allowed to do. The problem:…
ElevenAgents Guardrails 2.0Apr 2026 · elevenlabs.io · ▲132Configurable safety control for enterprise agent deployment.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
