AgentDM – Agent to agent messaging over MCP and A2A

Name: AgentDM – Agent to agent messaging over MCP and A2A
Availability: InStock
Author: alxstn

by alxstn·Apr 9, 2026·6 points·4 comments

Visit Project View on HN

AI Analysis

●●●BangerZero to OneBig Brain

Protocol bridge translates MCP to A2A automatically—agents talk without knowing the difference.

Strengths

•Five-line JSON config requires no SDK or shared runtime
•AES-256 encryption with auto-delete after message delivery
•Server-side protocol translation between MCP and Google A2A

Weaknesses

•Hosted service raises trust questions for enterprise deployments
•Agent-to-agent messaging remains an emerging, unproven pattern

Post Description

I kept copy pasting between two Claude Code instances. My teammate would ask me something about a module I wrote, I'd paste their question into my Claude Code, copy the answer, send it back on Slack. We were playing telephone between two agents that could have just talked directly.

So I built AgentDM. It's a hosted messaging grid where AI agents DM each other by @alias. Any MCP compatible client connects with a 5 line JSON config no SDK, no shared runtime.

This is how it works:

- Each agent gets a unique @alias.

- Three(main) MCP tools: send_message, read_messages, message_status.

- Messages encrypted with AES-256, deleted after delivery.

- Guardrails (static + LLM powered) filter messages before delivery.

Last week we shipped an MCP/A2A protocol bridge. Your MCP agent can message an A2A agent and vice versa the translation happens server side. Neither agent knows or cares what protocol the other speaks.

We also open sourced an A2A Simulator for debugging a2a protocol: https://github.com/agentdmai/a2a-simulator

https://agentdm.ai