Today, we’re announcing support for remote MCP servers in Claude Code. Connect your favorite tools and data sources to personalize your coding experience without needing to manage local servers.
Today, we’re announcing support for remote MCP servers in Claude Code. Connect your favorite tools and data sources to personalize your coding experience without needing to manage local servers.
Using Claude Code as your primary development interface
Claude Code can access both tools and resources exposed by MCP servers, giving it the ability to pull context from your third-party services—such as dev tools, project management systems, and knowledge bases—and take actions within those services.
You can integrate Claude Code with any remote MCP server, and the growing ecosystem of servers means that new capabilities are constantly coming online.
For example, by integrating Claude Code with the Sentry MCP server, you can access errors and issues from Sentry. Then, you can debug using the context of those issues without leaving your terminal.
You can also integrate Claude Code with the Linear MCP server to work with the context of your active projects.
“Linear's MCP integration brings Linear projects and issues directly into Claude Code,” shares Tom Moor, Head of Engineering at Linear. “With structured, real-time context from Linear, Claude Code can pull in issue details and project status—engineers can now stay in flow when moving between planning, writing code, and managing issues. Fewer tabs, less copy-paste. Better software, faster.”
Remote MCP servers offer a lower maintenance alternative to local servers: just add the vendor’s URL to Claude Code—no manual setup required. Vendors handle updates, scaling, and availability, so you can focus on building instead of managing server infrastructure.
Claude Code also features native OAuth support for remote MCP servers, ensuring secure connections to your existing accounts. Simply authenticate to your servers once, and Claude Code handles the rest—no API keys to manage or credentials to store.
Getting started
Remote MCP server support is available now in Claude Code. View the documentation to get started or explore our MCP directory with recommended servers.
Read the original article
Comments
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.
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.
For the curious and lazy, said book appears to be https://leanpub.com/creatingmcpserverswithoauth
For more curious and lazy people -- what are elicitations?
By zackify 2025-06-2311:29 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
By vessenes 2025-06-247:19 This is an extremely helpful bit of information about Oauth scope. THANK YOU
By stingraycharles 2025-06-228:383 reply 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.
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.
> 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.
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.
By wunderwuzzi23 2025-06-2215:42 ChatGPT Codex has internet access since a few weeks ago. It's super configurable on where it can connect to.
By anuramat 2025-06-2215:55 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
https://github.com/ruvnet/claude-code-flow adds some of the multiagent features ontop
By stingraycharles 2025-06-2210:57 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.
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.
By stingraycharles 2025-06-231:46 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.
By owebmaster 2025-06-231:471 reply > The aider slowdown is a real bummer.
Quite ironic isn't it?
By vessenes 2025-06-247:20 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.
By CharlieDigital 2025-06-2210:47
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.> Javascript community suddenly got automatic code creation agents, and went to town.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..?
By vessenes 2025-06-2214:29 Ironically the updates make it hard to get llm coding support for it. Very ironically.
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
By diggan 2025-06-2211:13 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?
By adhamsalama 2025-06-236:17 Cursor was sold for hundreds of millions? Wasn't Windsurf sold for $3 billion? And Cursor is more popular.
By adhamsalama 2025-06-236:17 Cursor was sold for hundreds of millions? Wasn't Windsurf sold for $3 billion? And Cursor is more popular.
By joshwarwick15 2025-06-226:442 reply List of servers to connect to here: https://github.com/jaw9c/awesome-remote-mcp-servers
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.
By hirsin 2025-06-2212:56 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.
By digitcatphd 2025-06-226:49 Thanks!!!
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].
[2] https://ninja.ai
I've found this from an old-school systems geek to be useful https://github.com/giantswarm/mcp-debug -- especially its REPL mode
By mark_undoio 2025-06-2212:39 Thanks for this - I've been using the MCP Inspector https://modelcontextprotocol.io/docs/tools/inspector but find it doesn't really fit my workflow.
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).
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.
By sagarpatil 2025-06-232:29 https://chorus.sh/ has a BYOK version Openwebui
