Agent Action Protocol (AAP)
MCP got us started, but is insufficient
Details
- External ID
- 47235632
- Source
- HN
- Company
- —
- Product
- Agent Action Protocol (AAP)
- Website domain
- github.com
- Launched
- March 3, 2026
- Cohort
- —
- Upvotes
- 13
- Upvotes percentile
- 0.6660516605166051
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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 place. We need a standard protocol for whenever an agent is taking action. Anywhere.I'm almost certainly the wrong person to design this, but I'm seeing more and more people tack things on to MCP rather than fix the underlying issues. The fastest way to get a good answer is to submit a bad one on the internet. So here I am. I think we need a new protocol. Whether it's AAP or something else, I submit my best effort.Please rip it apart, lets make something better.
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- agent communication protocol
- Manually corrected
- False
Could you build this?
Yes Creating a protocol specification and reference middleware for validating and gatekeeping AI tool actions can be rapidly built using standard schemas and proxy code.
Discussion
2 comments analyzed.
Competitors mentioned: Skills, MCP (Model Context Protocol), Function calling, REST APIs, CLI
Concerns raised: Over-specced and over-constrained design, Unclear positioning relative to MCP, Complexity compared to existing solutions
Competitors
Other products that read as similar to this one — 122 launches clear the similarity bar, closest 8 shown.
Attention rank: #42 of 123 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 111 days after the earliest competitor.
- Trust Protocols for Anthropic/OpenAI/Gemini · hn · 2026-02-18 · 40 upvotes · similarity 0.49
- MCP is for tools. A2A is for agents. What's for websites? · hn · 2026-04-12 · 5 upvotes · similarity 0.45
- Durable Actor Session Protocol · hn · 2026-09-28 · 17 upvotes · similarity 0.44
- Open-source browser for AI agents · hn · 2026-03-11 · 155 upvotes · similarity 0.44
- SentinelAgent Guard · ph · 2026-09-23 · 2 upvotes · similarity 0.43
- MCP Isn't Dead. You're Just Using It Wrong · hn · 2026-03-17 · 6 upvotes · similarity 0.42
- Risk Analysis Database of Every MCP Server · hn · 2026-02-05 · 22 upvotes · similarity 0.42
- Abject: the first self-aware object runtime · hn · 2026-04-02 · 10 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.