# What would you do with an MCP server?

**URL:** <https://discourse.devontechnologies.com/t/what-would-you-do-with-an-mcp-server/86828>\
**Category:** Artificial Intelligence\
**Created:** [April 29, 2026, 3:50pm UTC](https://discourse.devontechnologies.com/t/what-would-you-do-with-an-mcp-server/86828 "2026-04-29T15:50:43Z")\
**Posts on this page:** 1\
**Showing post:** 54

<div class="post-metadata">

**Author:** ![TomBen](https://discourse.devontechnologies.com/user_avatar/discourse.devontechnologies.com/tomben/32/23593_2.png) [@TomBen](https://discourse.devontechnologies.com/u/TomBen)\
**Post date:** [May 6, 2026, 5:27pm UTC](https://discourse.devontechnologies.com/t/what-would-you-do-with-an-mcp-server/86828/54 "2026-05-06T17:27:34Z")

</div>

For me, the most crucial feature for the MCP (or better CLI-based skill) is retrieving search results within the documents, like the current GUI results. So AI agents can view the search results like humans.

> [@\[Release\] DEVONthink CLI + Agent Skill](https://discourse.devontechnologies.com/t/release-devonthink-cli-agent-skill/86668/19):
>
> DEVONthink CLI is cool. However, I would suggest to output the specific results within the document, instead of the document only. For example, I used dt search "nationalism", its output is like: Results: - Item 1 Id: 2206588 Uuid: 03CF4017-1689-4112-9213-E96C1EA37FD0 Name: Nakai - 2025 - Nationalism and Environmentalism from the Global Perspective Path: /Users/username/Library/... Location: /Research/Nationalism/... Record Type: PDF document Kind: PDF+Text Cre…

---

_[View the full topic](https://discourse.devontechnologies.com/t/what-would-you-do-with-an-mcp-server/86828)._