# How Software Trusts Software: MCP, A2A, & the Registries Agents Use

**URL:** <https://forum.devtalk.com/t/how-software-trusts-software-mcp-a2a-the-registries-agents-use/250929>\
**Category:** AI In The News\
**Tags:** via-news-bot, mcp, a2a, in-the-news\
**Created:** [20 October 2026 04:25 UTC](https://forum.devtalk.com/t/how-software-trusts-software-mcp-a2a-the-registries-agents-use/250929 "2026-10-20T04:25:57Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![CommunityNews](https://forum.devtalk.com/user_avatar/forum.devtalk.com/communitynews/32/1113_2.png) [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\
**Post date:** [20 October 2026 04:25 UTC](https://forum.devtalk.com/t/how-software-trusts-software-mcp-a2a-the-registries-agents-use/250929/1 "2026-10-20T04:25:57Z")

</div>

> There is growing concern among security professionals that developers are treating protocols for connecting AI agents such as Model Context Protocol (MCP) and Agent2Agent (A2A) as though they were trust services, when neither was designed to vouch for what it connects, or is connecting to. A recent USENIX Security study, for example, found that roughly

Read in full here:

> **[How Software Trusts Software: MCP, A2A, & the Registries Agents Use](https://redmonk.com/kholterhoff/2026/10/19/mcp-a2a-registries-agents/)**
>
> There is growing concern among security professionals that developers are treating protocols for connecting AI agents such as Model Context Protocol (MCP) and Agent2Agent (A2A) as though they were trust services, when neither was designed to vouch...