This is great. As someone who has made a few MCP servers in the last few months, MAN this spec moves fast; well ahead of Anthropic's internal support for it, and well ahead of documentation for implementation. It's like the Javascript community suddenly got automatic code creation agents, and went to town..
That said, the original spec needed some rapid iteration. With https support finally in relatively good shape, I hope we'll be able to take a year to let the API dust settle. Spec updates every three months are really tough, especially when not versioned, thoroughly documented, or archived properly.
zackify
It has been moving fast.
One weird thing I found a few weeks ago, when I added my remote MCP to Claude's integration tab on the website, I was getting OAuth errors.
Turns out they are requiring a special "claudeai" scope. Once I added that to my server, I was able to use it remotely in claude desktop!
I couldn't find any docs or reasons online for them requesting this scope.
Also, I have been using remote mcps in claude code for weeks with the awesome mcp-remote proxy tool. It's nice to not need that any longer!
Then as I'm writing a book currently on MCP Servers with OAuth, Elicitations come out! I'm rushing to update this book and be the best source for every part of the latest spec, as I can already see lots of gaps in documentation on all these things.
Huge shout out to VS Code for being the best MCP Client, they have support for Elicitations in Insiders already and it works great from my testing.
vessenes
This is an extremely helpful bit of information about Oauth scope. THANK YOU
For more curious and lazy people -- what are elicitations?
zackify
Just call them “web forms” for LLMs.
You can ask the client to fill in a dropdown or input.
Example they give is a restaurants table booking tool.
Imagine saying book a table at 5pm. But 5pm is taken.
You can “elicit” the user and have them select from a list of available times
stingraycharles
Yeah, security really is an afterthought with most of these tools, but man the community is moving insanely fast — probably because most of these people are using these automation tools to develop their MCP servers in the first place.
It’s interesting to see other tools struggling to keep up. ChatGPT supposedly will get proper MCP client support “any day now”, but I don’t see codex supporting it any time soon.
Aider is very much struggling to adapt as well, as their whole workflow of editing and navigating files is easily replaced by MCP servers (probably better as well, as it provides much effective ways of reducing noise vs signal), so it’ll be interesting to see how tools adapt.
I’d love for Claude Code (or any tool for that matter) to fully embrace the agentic way of coding, e.g. have multiple agents specialize in different topics and some “main” agent directing them all. Those workflows seem to be working really well.
ljm
The real security issue is around the use of ‘YOLO mode’ where you just let the agent invoke tools in a completely unattended manner. It’s not much different than slapping sudo in front of every shell command or running as root.
People are going to continue doing that because these agentic tasks can take some time to run and checking in to approve a command so often becomes an annoyance.
I can’t see a way around that except to have some kind of sandboxing or a concept of untrusted or tainted input rather than treating all tokens as the same. Maybe a way of detecting if the response of a tool is within a threshold of acceptability within the definition of the MCP (which is easier with structured output), which is used to force a manual confirmation or straight up rejection if it’s deemed to be unusual or unsafe.
samcat116
> I can’t see a way around that except to have some kind of sandboxing or a concept of untrusted or tainted input rather than treating all tokens as the same. Maybe a way of detecting if the response of a tool is within a threshold of acceptability within the definition of the MCP (which is easier with structured output), which is used to force a manual confirmation or straight up rejection if it’s deemed to be unusual or unsafe.
I think we are starting to see these remote agent environments where each agent session gets its own sandbox environment to run things in. I bet thats where this is going.
alvis
It's indeed an issue. I love codex that it contains everything in a sandbox and I can review what has changed. It's proper and I've much better idea what's going on.
That said, I ditched codex for claude code... Sorry open ai. No MCP and no way to interact during execution is a huge drawback.
wunderwuzzi23
ChatGPT Codex has internet access since a few weeks ago. It's super configurable on where it can connect to.
anuramat
anthropic provides a custom devcontainer for sandboxing, but I have fallen in love with bubblewrap - it's a single command, and I get to keep all the infrastructure: e.g. it can do nix flakes without duplicating every derivation
Yeah that’s what I’m experimenting with, but I think it’s overengineered, especially with the whole dogmatic SPARC approach. I’m personally a more minimalistic person, and I would prefer it to be natively integrated into the app and being able to define exactly the (system) prompts for each of the agents.
vessenes
The aider slowdown is a real bummer. I’d love to have Claude code UI with the model choice aider gets me, but I’m not willing to give up tool integration.
stingraycharles
There are a dozen of PRs that are not getting accepted, I’m using a custom Aider build and tested their MCP client support but it’s just not getting merged nor reviewed.
owebmaster
> The aider slowdown is a real bummer.
Quite ironic isn't it?
vessenes
I imagine he might be burned out. HUGE project, hundreds of issues. He started as a crazy productive solo dev (on this project at least). Now it's an important open source project.
CharlieDigital
> Javascript community suddenly got automatic code creation agents, and went to town.
I've been working on an MCP server[0] that let's LLMs safely and securely generate and execute JavaScript in a sandbox including using `fetch` to make API calls. It includes a built in secrets manager to prevent exposing secrets to the LLM.
I think this unlocks a lot of use cases that require code execution without compromising security. Biggest one is that you can now ask the LLM to make API calls securely because the JS is run in a C# interpreter with constraints for memory, time, and statement limits with hidden secrets (e.g. API keys).
The implementation is open source with sample client code in JS using Vercel AI SDK with a demo UI as well.
> Spec updates every three months are really tough, especially when not versioned, thoroughly documented, or archived properly.
Couldnt AI help with that..?
vessenes
Ironically the updates make it hard to get llm coding support for it. Very ironically.
rvnx
The crazy thing about things moving fast is that people bought Cursor for hundreds of millions when it is already outdated by Claude Code. Very foolish by the purchasers but very smart for the founders
diggan
I think this is why we're seeing founders selling so quickly with these startups. You could wait some weeks or months to sell higher, but seems chances are higher that whatever you've built is outdated by then so why risk it?
adhamsalama
Cursor was sold for hundreds of millions? Wasn't Windsurf sold for $3 billion? And Cursor is more popular.
adhamsalama
Cursor was sold for hundreds of millions? Wasn't Windsurf sold for $3 billion? And Cursor is more popular.
That's great! It would be even better if one of the features included in the table was whether given MCP supports OAuth Dynamic Client Registration, which optional in the MCP standard.
hirsin
The MCP server technically doesn't support DCR. The authorization server for the MCP server does, which is a minor distinction.
Have you seen significant need for this? I've been trying to find data on things like "how many MCP clients are there really" - if it takes off where everything is going to be an MCP client && dynamically discovering what tools it needs beyond what it was originally set up for, sure.
digitcatphd
Thanks!!!
schappim
This is great news; remote MCP support should be open and accessible.
For what it’s worth, I’ve been using WitsyAi: it’s fully free, open source, and serves as a universal desktop chat-client (with remote MCP calling). You just need to BYO API keys.
Remote MCPs are close to my heart; I’ve been building a “Heroku for remote MCP tools” over at Ninja[2] to make it easy for people to spin up and share MCP tools without the usual setup headaches.
Lately, I’ve also been helping folks get started with MCP development on Raspberry Pi. If you’re keen to dive in, feel free to reach out [3].
I like the fact this mcp-debug tool can present a REPL and act as a mcp server itself.
We've been developing our MCP servers by first testing the principle with the "meat robot" approach - we tell the LLM (sometimes just through the stock web interface, no coding agent) what we're able to provide and just give it what it asks for - when we find a "tool" that works well we automate it.
This feels like it's an easier way of trying that process - we're finding it's very important to build an MCP interface that works with what LLMs "want" to do. Without impedance matching it can be difficult to get the overall outcome you want (I suspect this is worse if there's not much training data out there that resembles your problem).
yewenjie
Does anybody know of a cross-platform LLM-frontend with sync that is also open-source? I am currently using the web version of LobeChat on macOS and Android, but it's quite slow and has some features missing.
I really wish that MCP servers were configurable in the iOS app, and that there were more configuration options for connecting MCP servers in claude.ai, such as adding custom HTTP headers.
anotherpaul
If I understand correctly MCP is the interface to connect any API to LLMs.
Now a lot of people use it to add context to their model. And also tool calls?
I am using continue.dev not Claude but I imagine this tech stack will be ported everywhere.
As a python Dev I don't quite yet understand though how and what service I should be running. Or be using. Tbh. Can anyone ELI5?
beatthatflight
easiest one to get going with is to add the Playwright MCP. As a python dev you might have used it to do test automation? Anyway, it gives your tool eg Cursor, Claude Code access to the browser and automation using playwright. Meaning it can literally load a page to confirm its own change just had the desired effect.
The blender one is also fun as a starting point, if you do any 3d modelling (or even if you don't).
jasonjmcghee
You can give LLMs useful tools to have more rich interactions with them - help them help you more.
Documentation everywhere is still mostly outdated with the recent changes.
Anthropic having created MCP should not be outdated though I agree ..
That MCP remote workaround is no longer necessary
a_bonobo
It seems like all MCP functionality focuses on desktop-level apps like Claude Code. Are there any people building things like Shiny web apps that talk to MCP servers in the background to answer user questions? The only one I can find is acquaint WIP https://github.com/posit-dev/acquaint/pull/34
anthonypasq
i think this is coming very shortly. it was just extremely difficult to ship a remote mcp server with proper auth until like 1 week ago. its still barely there, but i think its coming. Every single client side chatbot can suddenly be 100x more effective in its ability to actually do stuff in the app.
rane
How is this different from the existing MCP support in Claude Code?
WXLCKNO
Existing MCP support was for the stdio and SSE transport protocols which are either local MCP servers in docker/node/python or a remote server but still requiring a sort of workaround running locally in the form of the mcp-remote non package.
This now natively supports the latest streamable http transport protocol and the server is entirely remote, nothing is running on your local machine it's just an url (usually ending with /mcp, although not mandatory it's usually true and distinguishes from /sse servers).
quleap
Claude Code had been supporting SSE transport without requiring mcp-remote.
So I don't really understand what's new in this announcement.
Maybe what's actually new is streamable HTTP and OAuth?
THANK YOU! I really thought I have a perversive mind looking at them all. At least, I'm not the only one. (Anthropic is definitely the butt of them all.)
void-star
Right??? Anthropic in particular seems to have directly cribbed from Kurt Vonnegut… and then, made it brown?
On a related note what’s the hesitation for Anthropic/OpenAI to open up their mobile apps to diy mcp servers?
conception
Probably app approvers and dealing with that muck?
iddan
I'm using https://xander.bot, which already leverages MCP connection between Claude Code and Linear. Really awesome stuff, how it knows how to gather context from Linear.
Aeolun
Unless you try to add Github, and it fails everywhere :/
WXLCKNO
Yeah it's word because GitHub (the new remote MCP server) respects the spec but oauth doesn't pop up.
You have to get a personal access token instead and pass it in the command when you do "claude mcp add" , I'm sorry I don't have the exact format in front of me right now but you should be able to get it working with that.
It's basically an adapted version of the GitHub remote MCP server instructions that uses the token
CharlesW
Which MCP servers are Claude Code must-adds for coding (vs. ancillary tasks like managing Jira)? For example, @kazuph/mcp-fetch has been useful.
rane
Just created this one to make it really easy for CC to interact with non-Anthropic reasoning models, in case of tough problems or just to get a second opinion on things.
I searched for this mcp server just to see what it was, and afaict Claude Code has all of these features built in already.
What is the additional functionality?
CharlesW
You may be right, I'm fairly new to Claude Code. CC itself summarized the difference this way: "Use MCP Fetch [the tool I refernced] when you need complete content or images, use WebFetch [CC's built in tool] when you want AI to extract specific information from a page."
unshavedyak
I added a MCP LSP a while back and as far as i can tell, CC doesn't even use it. Is there a trick to getting CC to actually.. use the MCP? I've not explicitly asked it to use the MCP, but it's an LSP (Rust Analyzer specifically) so it feels like the LLM should just use that in place of greping so much.
Are they all very explicit requests? I was hoping plugging an MCP into it would just make it more capable automatically
CharlesW
I was just wonering this myself, and the Context7 recommendation led me to these examples on its repo:
- Create a basic Next.js project with app router. use context7
- Create a script to delete the rows where the city is "" given PostgreSQL credentials. use context7
I feel like that Claude Code has independently invoked MCP Fetch a couple of times in the course of hundreds of interactions, but yes — it looks like specifically invoking them is the norm, at least until LLMs get better at matching tools to requests.
jasonjmcghee
Ah- I missed it extracts images from the pages. I don't think Claude does this. But you can fetch pages and give it images (separately).
WXLCKNO
Claude has web search as a tool built in but I'm not sure why it's kinda slow?
You can get the brave web search MCP with a free tier API key and it's super fast, combine that with the fetch MCP and it grabs information online really quickly.
nvahalik
Used this Friday to have Claude do some stuff but telling it to read a Linear ticket and make appropriate changes. Not perfect but saved me 15 minutes.
max_on_hn
If you like that workflow you might love the tool[0] which I built specifically to support it: CheepCode connects to Linear and works on tickets as they roll in, submitting PRs to GitHub.
1. Our tickets are sometimes "unqualified" and don't have enough information for a human to work on them (let alone an AI agent).
2. Tickets can be created on accident or due to human error and would then result in time spent working on things that don't matter.
3. AI tends to write code that violates our own "unwritten rules" and we are still in the process of getting our rules written down so that our own agentic workflows work properly.
I could definitely see the value in this for certain types of updates, but unfortunately it wouldn't work for our system.
richardblackbox
This is great, we have recently released on the blackboxai vscode agent a live call with the coding agent
Will be trying the MCP with the live call as well, i think it should work
efitz
This would be interesting if it also included changing MCP to support websockets.
lsaferite
The spec already supports this by explicitly allowing for custom transports. That being said, there's no standard for WebSocket right now.
I feel like the specific transports should be their own specs TBH. That would allow a lot a flex around this stuff and it would decouple transport changes from main protocol changes.
michaericalribo
When will Gemini release a desktop app and enable MCP and coding agents??
mark_undoio
I assume you're aware but there are some open source assistants that can get you this (at least to some extent).
Which I think supports Gemini among with all the other major AI providers, plus MCP. I have heard anecdotally that it doesn't work as well as Claude Code, so maybe there are additional smarts required to make a top notch agent.
I've also heard that Claude is just the best LLM at tool use at the moment, so YMMV with other models.
artdigital
Not a desktop app, but Gemini has “Jules” which is their autonomous coding agent
You hook up your GitHub repo and it’ll clone it, setup the env and then work on the task you give it
fizx
Cursor + Gemini is rather good.
yahoozoo
It would be nice if they increased their context windows. I was trying out the Ghidra MCP and it’s pretty easy to run through the context window.
sumedh
Looks like the issue is with Ghidra MCP
indigodaddy
If you’re on the Claude Pro plan and on a forced break, this tool might be useful:
I put 10 months of work into MCP. Been a Max 20 x subscriber since Day 1. Spent thousands via the API previously. Anthropic randomly banned my account with no warning or explanation last week. I've had to spent significant time and resources moving AWAY from MCP.
Do not get comfy with any of these protocols or companies. They can destroy your workflows and livelihood in an instant.
jasonjmcghee
Reach out to support. Unless you were doing something egregiously against terms of use, I doubt you'll have trouble getting your access restored.
Also- Claude desktop is honestly one of the more minimal implementations of an mcp client with a bunch of missing features. Just search for mcp clients. There are many you can use.
geeunits
I did. No response. Filled out the form, no response. I've genuinely no idea what I could've done, outside of complain about the palantir xs scripting issue. Quite disheartening. Thanks for the tip!
Aeolun
What does MCP has anything to do with Anthropic or Claude Max? I mean, they made the protocol, but it works everywhere.
geeunits
They invented the protocol? I used Claude Desktop extensively in testing. No other local clients currently interop very well with MCP Tooling. They're more of an afterthought for other clients.
Aeolun
Sure, but it’s not suddenly useless to you because Anthropic restricts you. Those 10 months of building MCP servers are still of use, even if I can only imagine how frustrating losing Claude Max must be (recent x20 subscriber here)
geeunits
The difference is, they were being used. Now they'll only be of use further down the line, and I have to readjust my daily workflow. Just because. It's highly frustrating and makes me regret putting so much effort in embracing 'the Anthropic way' when a rug pull can come out of nowhere. I wish I'd put that effort into my own tooling instead. Just a fair warning to anyone getting comfortable.
> No other local clients currently interop very well with MCP Tooling
Not even close to true - VSCode and cursor both have MCP support, and INE VSCode’s is great.
Also, I’m curious about your claim to have spent 10 months building MCP servers, as the spec has only been out since the end of November - which is ~7 months.
geeunits
VSCode won't iterate without constant permissions/interrupts. No thanks Cursor.
10 months must have been hyperbole but I've moved two states and a country in that time, apologies.
smrtinsert
He's downvoted but does anyone remember Twitters early years?
That said, the original spec needed some rapid iteration. With https support finally in relatively good shape, I hope we'll be able to take a year to let the API dust settle. Spec updates every three months are really tough, especially when not versioned, thoroughly documented, or archived properly.
One weird thing I found a few weeks ago, when I added my remote MCP to Claude's integration tab on the website, I was getting OAuth errors.
Turns out they are requiring a special "claudeai" scope. Once I added that to my server, I was able to use it remotely in claude desktop!
I couldn't find any docs or reasons online for them requesting this scope.
Also, I have been using remote mcps in claude code for weeks with the awesome mcp-remote proxy tool. It's nice to not need that any longer!
Then as I'm writing a book currently on MCP Servers with OAuth, Elicitations come out! I'm rushing to update this book and be the best source for every part of the latest spec, as I can already see lots of gaps in documentation on all these things.
Huge shout out to VS Code for being the best MCP Client, they have support for Elicitations in Insiders already and it works great from my testing.
For more curious and lazy people -- what are elicitations?
You can ask the client to fill in a dropdown or input.
Example they give is a restaurants table booking tool.
Imagine saying book a table at 5pm. But 5pm is taken.
You can “elicit” the user and have them select from a list of available times
It’s interesting to see other tools struggling to keep up. ChatGPT supposedly will get proper MCP client support “any day now”, but I don’t see codex supporting it any time soon.
Aider is very much struggling to adapt as well, as their whole workflow of editing and navigating files is easily replaced by MCP servers (probably better as well, as it provides much effective ways of reducing noise vs signal), so it’ll be interesting to see how tools adapt.
I’d love for Claude Code (or any tool for that matter) to fully embrace the agentic way of coding, e.g. have multiple agents specialize in different topics and some “main” agent directing them all. Those workflows seem to be working really well.
People are going to continue doing that because these agentic tasks can take some time to run and checking in to approve a command so often becomes an annoyance.
I can’t see a way around that except to have some kind of sandboxing or a concept of untrusted or tainted input rather than treating all tokens as the same. Maybe a way of detecting if the response of a tool is within a threshold of acceptability within the definition of the MCP (which is easier with structured output), which is used to force a manual confirmation or straight up rejection if it’s deemed to be unusual or unsafe.
I think we are starting to see these remote agent environments where each agent session gets its own sandbox environment to run things in. I bet thats where this is going.
That said, I ditched codex for claude code... Sorry open ai. No MCP and no way to interact during execution is a huge drawback.
Quite ironic isn't it?
I think this unlocks a lot of use cases that require code execution without compromising security. Biggest one is that you can now ask the LLM to make API calls securely because the JS is run in a C# interpreter with constraints for memory, time, and statement limits with hidden secrets (e.g. API keys).
The implementation is open source with sample client code in JS using Vercel AI SDK with a demo UI as well.
[0] https://github.com/CharlieDigital/runjs
Couldnt AI help with that..?
Have you seen significant need for this? I've been trying to find data on things like "how many MCP clients are there really" - if it takes off where everything is going to be an MCP client && dynamically discovering what tools it needs beyond what it was originally set up for, sure.
For what it’s worth, I’ve been using WitsyAi: it’s fully free, open source, and serves as a universal desktop chat-client (with remote MCP calling). You just need to BYO API keys.
Remote MCPs are close to my heart; I’ve been building a “Heroku for remote MCP tools” over at Ninja[2] to make it easy for people to spin up and share MCP tools without the usual setup headaches.
Lately, I’ve also been helping folks get started with MCP development on Raspberry Pi. If you’re keen to dive in, feel free to reach out [3].
[1] https://witsyai.com
[2] https://ninja.ai
[3] https://calendly.com/schappi/30min
I like the fact this mcp-debug tool can present a REPL and act as a mcp server itself.
We've been developing our MCP servers by first testing the principle with the "meat robot" approach - we tell the LLM (sometimes just through the stock web interface, no coding agent) what we're able to provide and just give it what it asks for - when we find a "tool" that works well we automate it.
This feels like it's an easier way of trying that process - we're finding it's very important to build an MCP interface that works with what LLMs "want" to do. Without impedance matching it can be difficult to get the overall outcome you want (I suspect this is worse if there's not much training data out there that resembles your problem).
Now a lot of people use it to add context to their model. And also tool calls?
I am using continue.dev not Claude but I imagine this tech stack will be ported everywhere.
As a python Dev I don't quite yet understand though how and what service I should be running. Or be using. Tbh. Can anyone ELI5?
The blender one is also fun as a starting point, if you do any 3d modelling (or even if you don't).
They're also fun and easy to build.
Here's one I made - it wraps the vscode debugger: https://github.com/jasonjmcghee/claude-debugs-for-you
I've specifically tested it with continue.dev so it might serve as a useful example / template.
it allows publishing any text or claude artifact directly from the claude.
I have made it mostly for fun and as an experiment to try what is possible.
The CloudFlare and Linear MCP servers (at a minimum) seem to use the same approach, the mcp-remote npm package, e.g.
https://github.com/cloudflare/mcp-server-cloudflare/tree/mai...
But mcp-remote is clearly documented as experimental:> Note: this is a working proof-of-concept but should be considered experimental
https://www.npmjs.com/package/mcp-remote
I'm not sure how this could be considered anything other than professional negligence. I'm reminded of Kyle Kingsbury's CraftConf talk, Hope Springs Eternal: https://theburningmonk.com/2015/06/craftconf15-takeaways-fro...
Anthropic having created MCP should not be outdated though I agree ..
That MCP remote workaround is no longer necessary
This now natively supports the latest streamable http transport protocol and the server is entirely remote, nothing is running on your local machine it's just an url (usually ending with /mcp, although not mandatory it's usually true and distinguishes from /sse servers).
So I don't really understand what's new in this announcement.
Maybe what's actually new is streamable HTTP and OAuth?
https://github.com/anthropics/claude-code/blob/main/CHANGELO...
https://velvetshark.com/ai-company-logos-that-look-like-butt...
https://scienceleadership.org/blog/the_use_of_illustration_i...
You have to get a personal access token instead and pass it in the command when you do "claude mcp add" , I'm sorry I don't have the exact format in front of me right now but you should be able to get it working with that.
It's basically an adapted version of the GitHub remote MCP server instructions that uses the token
https://github.com/raine/consult-llm-mcp
What is the additional functionality?
Are they all very explicit requests? I was hoping plugging an MCP into it would just make it more capable automatically
- Create a basic Next.js project with app router. use context7
- Create a script to delete the rows where the city is "" given PostgreSQL credentials. use context7
I feel like that Claude Code has independently invoked MCP Fetch a couple of times in the course of hundreds of interactions, but yes — it looks like specifically invoking them is the norm, at least until LLMs get better at matching tools to requests.
You can get the brave web search MCP with a free tier API key and it's super fast, combine that with the fetch MCP and it grabs information online really quickly.
[0] https://cheepcode.com
1. Our tickets are sometimes "unqualified" and don't have enough information for a human to work on them (let alone an AI agent). 2. Tickets can be created on accident or due to human error and would then result in time spent working on things that don't matter. 3. AI tends to write code that violates our own "unwritten rules" and we are still in the process of getting our rules written down so that our own agentic workflows work properly.
I could definitely see the value in this for certain types of updates, but unfortunately it wouldn't work for our system.
Will be trying the MCP with the live call as well, i think it should work
I feel like the specific transports should be their own specs TBH. That would allow a lot a flex around this stuff and it would decouple transport changes from main protocol changes.
E.g. Codename Goose https://block.github.io/goose/docs/quickstart/
Which I think supports Gemini among with all the other major AI providers, plus MCP. I have heard anecdotally that it doesn't work as well as Claude Code, so maybe there are additional smarts required to make a top notch agent.
I've also heard that Claude is just the best LLM at tool use at the moment, so YMMV with other models.
You hook up your GitHub repo and it’ll clone it, setup the env and then work on the task you give it
https://github.com/robertpiosik/CodeWebChat
Do not get comfy with any of these protocols or companies. They can destroy your workflows and livelihood in an instant.
Also- Claude desktop is honestly one of the more minimal implementations of an mcp client with a bunch of missing features. Just search for mcp clients. There are many you can use.
Not even close to true - VSCode and cursor both have MCP support, and INE VSCode’s is great.
Also, I’m curious about your claim to have spent 10 months building MCP servers, as the spec has only been out since the end of November - which is ~7 months.
10 months must have been hyperbole but I've moved two states and a country in that time, apologies.