Posts tagged with "history"

The experiment with building an MCP server continues, with some hacking on it happening over a couple of hours while killing time in an Edinburgh coffee shop.

It is, of course, a solution looking for a problem, and I suspect I'm the only person who will ever use it, and even then only as a test, but building it is proving interesting.

The main changes in v0.2.0 are:

• I turned the current search_guide tool into a line_search_guide tool (because that's what it was doing: a line-by-line search).
• I added a body_search_guide tool that treats all the lines in an entry as a single block of text and then does the search in that (so searches over line breaks will work).
• I added a read_entry_source tool that, rather than rendering the entry of a guide as plain text with all the markup removed, it instead delivers the underlying "source" for the entry; something that could be useful if you wanted to get an agent to convert it into another marked-up body of text.
• I added a markup glossary resource, which technically tells an agent everything it needs to know about Norton Guide markup.

The latter one is interesting. I added it and did some experimenting locally and it seemed to be helpful and I could ask questions about markup and Copilot seemed to use it. Meanwhile, having installed v0.2.0 globally on my machine, and having enabled it, I'm finding that Copilot seems to have zero clue about the markup and instead is using the server to go off and read the guides to work out the markup¹.

On the other hand, the new "get source" tool seems to work a treat.

So I suspect I still have some reading/experimenting to do when it comes to resources, so I can better understand why I'd want to provide them and what problem they solve.

Recently I've been thinking that it would be interesting to get to know a little about the Model Context Protocol and see what it's about and get a feel for how useful it might be, if at all, for anything I do.

As always happens when I want to try out something new, I reached for a problem I know well so I don't have to get bogged down in solving the problem itself. As almost always happens, I decided I should base it around Norton Guides.

Part of the point of MCP seems to be providing an interface over sources of data and actions, that an LLM might not otherwise be able to cope with, and so it sounded to me like providing a bridge to the content of Norton Guide files would be a perfect test. Of course, this isn't the first time I've bridged LLMs and NG files, but this is obviously intended to be a more generic solution than throwing a Markdown file at NotebookLM.

Earlier this afternoon I sat down and did some reading, and then decided to throw the problem at GitHub Copilot. I told it I wanted to use my NGDB library as the core of the tool, and that it should wrap it up with FastMCP. The initial result was... a bit of a mess. It sort of worked, sort of, but it also seemed to try and put together a project that mostly looked how my Python repos look, but with some bits just wrong.

I did some cleaning up, did some testing, did some tweaking, and eventually I had something working.

So far I've given the code a fairly quick read over, and I can see what it's doing and how it's going about this. This approach obviously has the disadvantage that I didn't hand-write it so there's still a lot to read to really appreciate what's going on; on the other hand, it does have the advantage that it's implemented a tool based on my library so I know what to expect it to be doing.

There will be more code reading happening, and I also intend to look to tidy up the code more and perhaps hand-add some more features.

I very much doubt that this particular MCP server is going to be any use to anyone, but as a proof of concept it works well for me. If I were in a position of needing to build something genuinely useful, I now have a start and a vague idea.

On the other hand: once again, as with other projects I've done related to Norton Guides, this is a tool that helps keep the content available and accessible; that alone is one reason for me to tidy this up and move it towards v1.0.0 and keep it maintained.

If you fancy having a play, some (currently Copilot-generated) documentation can be found on the server's dedicated site. When I get a bit more time I'm going to flesh this out.

As I've mentioned a few times on this blog, I've long had a bit of a thing for writing tools for reading the content of Norton Guide files. I first used Norton Guides back in the early 1990s thanks to the release of Clipper 5, and later on in that decade I wrote my first couple of tools to turn guides into HTML (and also wrote a Windows-based reader, then rewrote it, wrote one for OS/2, wrote one for GNU/Linux, and so on).

One tool (ng2html) got used by a few sites on the 'net to publish all sorts of guides, but it's not something I ever got into doing myself. Amusingly, from time to time, because I had a credit on those sites as the author of the conversion tool, I'd get random emails from people hoping I could help them with the topic of whatever guide they'd been reading. Sometimes I could help, often not.

From what I've recently been told two of the biggest sites for this sort of thing (they might even have been the same site, or one a copy of the other, I didn't really dive into them too much and wasn't sure who was behind them anyway) have long since gone offline. This means that, as far as I can tell, a huge collection of knowledge from the DOS days is a lot harder to get to, if it hasn't disappeared altogether.

This makes me kind of sad.

Edit to add: digging a little, one of the sites was called www.clipx.net and it looks to have long-since gone offline. It is on archive.org though. The other was x-hacker.org which, digging a wee bit more, seems to have been a copy of what was on clipx.net.

So I had an idea: having recently polished up my replacement for ng2html, why not use that to build my own site that publishes the guides I have? So I set about it.

There's one wrinkle to this though. While the other sites seemed to just publish every NG file they got their hands on, I'd prefer to try and do it like this: publish every guide I have in my collection that I have a licence or permission to publish; or as near as possible¹

Given all of this, norton-guides.davep.dev has been born. The repository that drives it is on GitHub, and I have a wiki page that lists all the guides I have that I could possibly publish, showing what I know about the copyright/licence of each one and what the publishing state is.

So with this, I'm putting out a call for help: if you remember the days of Norton Guide help files, if you have Norton Guide help files I don't have, and especially if you are the copyright-holder of any of these files and you can extend me the permission to open them up, or if you know the right people and can get me in touch with them, DROP ME A LINE!

I'd also love to have others join me in this... quest. So if you want to contribute to the repository and help build it up I'd also love to hear from you.