In a recent Claude Code session I tried using the Google Docs, Drive, and Sheets MCP and was honestly surprised at how limited it felt. It was hard to get anything meaningful done because it just did not expose enough capability to be useful in practice. In hindsight, that frustration was probably a good thing. I ended up skipping MCP entirely and using the LaTeX API plus its plugin ecosystem, and the result was far beyond anything I could have realistically produced through Docs anyway.

I have seen a similar pattern with Canva’s MCP. I pay for Pro, but the one feature that would actually make MCP useful, Auto Fill, is gated behind an enterprise plan. So the surface is there, but the real power is locked away.

I get that this is still the wild west for MCP, and I agree with the OP’s general take. But right now there is a big gap between "integration exists" and "integration is actually useful." Personally, I am more excited about where something like WebMCP could go, where the default assumption is full capability rather than a restricted subset.

I agree. I also tried Figma’s MCP tools (wrote about it here - https://metedata.substack.com/p/metedata-digest-003-where-do...) and found it very underwhelming.

The result is less that I want to go to Figma directly and more that I just want to skip it entirely. So, assuming the power of these aggregator agents keeps growing, the onus is on these tools to create useful integrations or get subsumed by a model capability or another tool with a better integration. It sounds like your experience is similar - you bypassed the tools with bad integrations instead of going to them directly.

You have to be very very careful with this stuff. These SaaS companies have tons of paying customers giving them thousands of dollars a month. If customers mess up with an officially supported MCP and delete their assets or break implementations or DDOS their own site it’d be nightmare for sales / support.

It makes sense they very slowly transitioned from read-only to limited write. You have to carefully beta test. Both figuring out the guardrails and finding usecases where it actually works well. The only way to do that (properly) is a slow drip release cycle.

I'm sure that's part of it but I think it's a very small part of the story. They've been pushing hard on internal AI creation tools for a while, and those clearly didn't take hold.

IMHO MCP is the AppleScript/Shortcuts part of the internet. Never really took on Apple platforms (except for some hardcore fans); not sure it will ever actually take on the internet…

I had same experience with Databricks. The built-in MCP offering is very limited (querying, etc.) but there are community-built projects that offer the full scope (creating ETL jobs, etc.). I would prefer not to have to go through the hassle of getting some random project on GitHub added as an artifact and deal with the updates.

All SaaS-built MCP servers should cover the entirety their existing API functionality. I know it sounds like a lot but I really don't think it is an unreasonable expectation.

Isn't this basically What Color is Your Parachute?

Rust Underwater Labs

The one thing that really stands out about Christmas growing up was how amazing my dad was at giving gifts that sparked my curiosity about the world. Instead of focusing on toys and games, he often chose books (scientific) and kits (RadioShack). While today you can easily find gifts that combine fun and learning, growing up in the '70s and '80s, it was usually one or the other. That’s not to say I didn’t enjoy a good toy or game—they could also stimulate imagination and creativity—but it was the books and kits that truly shaped who I would become.

I also had an aunt who loved giving magazine subscriptions. Thanks to her, I had long-running subscriptions to Discover, Scientific American, Omni, and later BYTE. And, of course, the most important one of all: Dungeon!

I voluntarily left the workforce a few years ago, and I'm fortunate that my wife, a teacher, has a solid job earning over $100k a year. While that’s not a huge amount, it’s enough for us to live comfortably. What we discovered during this transition was eye-opening: most of my income had been going toward discretionary spending, much of it wasteful. Now, even though I only generate $200–$500 a month in passive income from a few books I sell on Amazon (gotta love passive income), we’re actually living better than before. This is thanks to paying off debt, living more within our means, and both of us feeling more personally fulfilled.

So, what do I do now? * Household management: I handle cooking (about half), cleaning, shopping, finances, repairs—basically all the day-to-day stuff. * Supporting my wife: I act as her personal assistant. I write emails, grants, and curriculum; create her presentations and visuals; and handle whatever else she needs so she can focus on teaching. With my help, she’s raised over $100k in two years to support her program—not too shabby! * Pet parent: I’m a proud cat and dog dad. Side projects: I’m working on a web app that I hope will generate income someday. * Writing a novel: For the first time, I’ve moved past the endless planning stage and am actually writing! I’ve also got more ideas in the works. * Tabletop game design: I have about ten tabletop games in various stages of development, and a few are done. I’d love to get at least one published. A friend and I even created a tabletop game that teaches condensed matter physics (CMP 101 level) with funding from an NSF grant. It’s more of a euro-game than an edu-game, and we’re looking to publish it and maybe turn it into an app. * Self-care: Decades of work, especially in startups, took a toll on me emotionally and physically. Today, I'm more organized, more productive, more focused, and more motivated than ever. I have a lot of work to do to repair my health, but I'm working on it.

What I’m finally able to do: * Engage in emotionally rewarding activities instead of draining ones. * Pursue personal goals and dreams I’ve always put on hold. * Channel my energy into supporting my wife, which has made her happier and more fulfilled in her career—a first for her. * Be the master of my own destiny rather than living on someone else’s terms.

I do feel some anxiety about putting the financial burden on my wife. She understands and values the contributions I make to our household and her career, so there’s no resentment on her part. Still, I worry about what would happen if she lost her job or couldn’t work. I cope by focusing on the fact that the things I’m pursuing can generate income. If I channel my energy positively and healthily into these pursuits, I believe they eventually will.

Me but a day ago.

I grew up in a shooting and hunting family. Whenever we were driving around town my dad would point out a wheel weight on the ground at a stop light/sign and my brother and I would jump out of the Land Cruiser and collect it. This was the 80s of course so we were drinking out of hose bibs, riding our bikes on high-traffic streets without helmets, and playing live Frogger to collect wheel weights. It was a game to my brother and I because wheel weights came in various shapes and sizes so it was fun to see if we could land a whopper. We would also stop by Tire stores and scour the parking lot for them. At some point we would melt the lead down into bars using a crucible. These would be later cast into bullets. My brother and I were also (in hindsight) child slave laborers that were tasked with reloading cartridges and shotgun shells for target shooting and trap/skeet. In our house this was considered a chore. This was our childhood. None of us ever used gloves or masks during any step in this process.

In a recent conversation over breakfast I brought up lead poisoning and my dad was adamant (in his conspiratorial way) about how all of that lead exposure via handling lead and inhaling lead fumes didn't result in any significant health problems for us. I'm assuming he meant that we all weren't dead yet. He's 80 and a wreck. He's had all sorts of health issues include recent cancer remission. I'm 55 and I've had nerve issues since my teenage years which manifests itself as a noticeable tremor in my right hand that has got worse over time. I developed adult onset asthma in my late teens. I have a host of other health conditions as well. Who knows how much of that is tied back to lead exposure.

I have done over a year of keto on two separate occasions and found it VERY easy to maintain. I contribute this to a high level of satiety while consuming foods high in healthy fats and protein. I rarely had cravings. My go-to fat is coconut oil which I put in my morning coffee and can add to just about any cooking and soups (coming up on soup season so bone broth and coconut oil is my go to). Just about anywhere you go out to eat you can find something that is keto-friendly. Anecdotally, during both of these stints I did not need to take my long term asthma medication and my frequency of use for my emergency inhaler was considerably lower.

I heard about keto diet and tried severely limiting sugar and other carbs intake. I instantly felt better and lost 6kg in two months. Sticking to the new diet was pretty easy. Now after 6 months I have constant headache, painkillers don't work, constantly tired and no further weight loss whatsoever. Every test was ok, sugar perfect, just insulin in upper bound of range. Limiting sugar is not panacea. Sometimes it works, sometimes it doesn't.

I personally had the opposite experience when it came to highly collaborative SMALL teams. In my last WFH project, lasting a couple of years, we worked 8 hours a day in a video call with our cameras turned on (most of the time). We did code collaboration in VSCode, design collaboration in Figma, and database/architectural collaboration in Miro. Everything else was via screen share. For our team it was HIGHLY effective. It didn't hurt that we all enjoyed working with each other. The choice to work in video calls with our cameras on was less about accountability and more about feeling connected. Nobody judged if your camera was off or you left the call. Easily the best years of my career.

In AI applications, especially those involving predictive modeling, MARS can be used to improve the accuracy of predictions. For example, MARS models are used in time series forecasting, financial predictions, environmental modeling, and other domains where relationships between inputs and outputs are complex and non-linear. By adding time-awareness, the model can handle time-based data more effectively.