Set up MCP access for a household wiki
They attached an MCP server to Wiki.js so an LLM could edit household pages.
- What they did
- The author’s wife wired an MCP server into their household Wiki.js. After that, an LLM was able to make updates to the wiki. The post does not name the server, model, or prompts, and it does not explain how a person reviews the changes.
- How it went
- The author said it was striking that an LLM could change the wiki at all. No concrete results, counts, or problems were reported.
- Tips
- Start with very tight permissions and a clear human checkpoint before any change is committed. If you test this, choose one page first and verify exactly what the agent is allowed to edit.
Try it yourself with Claude Code
I have a [wiki platform] instance at [URL] for a household wiki. Please outline how to connect it to an MCP server so an AI tool can inspect pages and prepare edits. Use the smallest possible permissions, then draft an update for [page name] and stop for my approval before you save, send, publish, or delete anything.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
1 more report of this
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Use a local agent for personal errands
A commenter uses a trusted local agent to handle travel, media conversion, ebook searching, design tweaks, and schedule tracking.
Let a sleep pose trigger a fan
They built a Raspberry Pi setup that watches sleeping posture and flips a fan on or off with a remote button pusher.
Screen job listings against your resume and salary targets
A job seeker uses an agent each morning to filter LinkedIn roles by level, pay, and resume fit before deciding what to pursue.
Turn handwritten appointments and PDFs into calendar entries
A developer built a private agent that reads appointment photos, adds events, searches email, and files PDFs into paperless.
Build a tutoring loop that tests, teaches, and retests
Hugh Shbalz set up an agent to assess students, create lessons for weak spots, and check mastery again afterward.
Rework Home Assistant lights for evening and sleep
They used an AI agent to change Home Assistant rules so harsh LEDs give way to softer strips, with a late-night shutdown and red sleep mode.