Building an MCP bridge

MCP was not clicking for me, so the best way to learn was to build a thing with it. I have a plethora of notes everywhere and now I have a machine that drops rough ideas into my publishing backlog.

MCP is basicly an api for AI that tells agents how it's supposed to be used.

Kalle Tolonen
16.9.2026

What agents do

Assistants can fill out ideas for backlog. Humans should still do the writing that isn't, for example, tech specs.

The problem

I need tech notes that are accessible for the tools that do the implementation. Publishing is a bonus that comes with minimal extra effort. I can go for a walk and talk with an AI and then ask it to post the summarized convo to my ideas.

10k view

Two routes to idea backlog:

What the MCP actually exposes

The MCP-endpoint is auth protected. Tools under the hood:

who does what

Handoff rules

Rough idea → create_article_idea (or update) → optional promote_article_idea → human writes and edits in the dashboard.

Is it in use?

Real examples already sitting as published items or drafts on the site:

Tradeoffs

More moving parts (assistants, MCP, backlog, dashboard) vs a simple todo. Probably useful to only me, since this is an eccentric niche blog.


Comments

No published comments yet.


Add a Comment

Your comment is held for review before it appears publicly.

Tick the box, then click Submit right away (Google expires the check after about two minutes).