Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Not a hack at all.
In fact, this is how Kubernetes APIs work. Even the CLI asks YAML or JSON content type when `-o yaml` or `-o json` is specified.
Also, some other sites (albeit sometimes looking at the User-Agent header, hence more hacky) also doing the same. For example `ipinfo.io` returns HTML page when opened in a browser but a JSON (prettified) when requested via cURL.
by pvtmert - Yes, we do use user agents to separate requests to our websites and API service. However, we request users to switch to api.ipinfo.io (dedicated API infrastructure) and use ipinfo.io/json for an explicit request for the API endpoint.
There are indeed some limitations to this implementation. The primary one being IPv6 support. The implementation prioritizes convenience over internet limitations, requiring us to roll out IPv6 dual stacking on the web request level as opposed to the DNS level. On an API level, this results in users with IPv6 addresses making API requests to v6.ipinfo.io.
So, last year we rolled out dedicated API infrastructure for api.ipinfo.io
by reincoder - > I wish the spec had some capability to mitigate for this
I like their solution. It feels like because remote MCP servers are built on HTTP that they are actually using the spec as intended. Serving html when asked for it.
by lorecore - MCP = Model Context Protocol, an interface for LLMs to retrieve information and perform actionsby gpvos
- But why would you show the MCP server URL as a clickable link in the first place, if it's not meant to be clicked? Put it in a monospaced box with a "copy to clipboard" button, it's not the fault of the user for not "thinking ahead" when they click a clickable link that wasn't actually meant to be clicked.by stavros
- All kinds of tools make it really difficult to not make a URL clickable and even if it wasn't clickable they might still put it in address bar...by blcknight
- I call this "dev think". Blames user for not thinking ahead when they themselves haven't thought ahead about how users use things. It's everywhere these days, as an end user of things myself, it's maddening.by tekchip
- Bearer tokens using mcp-remote are the pragmatic way forward out of the authentication mess.
Spec-based implementations of OAuth 2.0/2.1, including dynamic client registration and token exchanges, are absolutely necessary on a large scale but are an enormous barrier for adoption during early deployments. Cookie tricks ignore the spec and produce special cases when client credentials need to be rotated.
Solution in the real world: configure the server to provide the WWW-Authenticate header with value "Bearer" on unauthorized requests, issue limited-scoped tokens, leave the rest up to mcp-remote. The client authenticates once, uses bearer token in its requests, server verifies against scopes. No dynamic client registration required.
The authentication solution becomes clearer if you distinguish between "what the spec allows" and "what you need in your deployment." Not many servers really require OAuth on day 1.
by luodaint - I love this. The best documentation is that which is presented at the exact place and time that it is needed, and users self support really well if you do that.
I once worked for $COMPANY and we had a network scanning application. Always generated a lot of tickets from angry people wanting to scream about bots.
So we put a web page page on each worker that would inherit some details from whatever job was running, and say “I’m a $TYPE_OF_SCANNER FROM $COMPANY doing $THING_THAT_BENEFITS_YOU.
This behavior is covered by our terms of service page at $LINK.
If you believe that we should not be doing this, please contact $SUPPORT and provide this code:
$SCAN_JOB_IDENTIFIER”
Call volume and unhappy customers went way down.
by efitz - this reminds: webcrawlers are supposed to include an info url with their user agent header
ex: Googlebot/2.1 (+http://www.google.com/bot.html)
- I never quite understand why /mcp endpoint is needed.
You can still keep using Rest API with swagger docs and tell the AI to read the swagger docs. It's the same thing. The entire Rest API specification is a lot more flexible than the JSON RPC format /mcp uses.
by didip - rest api with swagger docs requires one extra hop to pull the details necessary to interact with the api, and it pollutes context in a similar way as mcp.
ideally what you would have is skills + scripts that the agent can load progressively to interact with the api
or even better: a single cli tool the agent is aware of, and which combines `--help` output with `tldr` tips, when the command is incomplete, and prints out helpful error messages when the incantation is wrong
- MCP is fine for exposing tools that don't have APIs, but wrapping an API is an MCP is fine if you like consistency.
Personally, for just tools, I wire up tool calls with context captured via system prompt.
by BoxedEmpathy - > I did something a little bit hacky: if the request is for GET /mcp and the Accept header includes text/html and NOT application/json or text/event-stream, I return a HTML page
Is this not the intended use of request headers?
by cyberge99 - I think so, but if you wanted to be pedantic you could make the argument that the same resource is not being served with the different Accept header. A welcome page is not the same thing as the JSON returned from the MCP spec.by lorecore
- Technically not really, it's supposed to be alternative versions of the same content.by PufPufPuf
- Excellent. Tiny affordances like this should be more commonplace, IMO.
I think this probably also helps when truly clueless users drop the link into an agent directly, because then the agent will relay the message to the user.
by zrail - i have experimented with this idea a bit
i have learned that if the request accepts html, just give them that, however, some agents will ask for text/markdown, so just give them that.
you can even take OPs ideas further: text/html? serve html help page; text/markdown? serve the same but pure text, maybe nudge the agent on how to install the mcp; application/json? pass through to the mcp app.
the whole llms.txt thing could have been that
- First time I access this website, as far as I know (via a corporate VPN, and the first time I see this kind of blocking from Cloudflare while using that VPN):
"Sorry, you have been blocked
You are unable to access hybridlogic.co.uk
Why have I been blocked?
This website is using a security service to protect itself from online attacks. The action you just performed triggered the security solution. There are several actions that could trigger this block including submitting a certain word or phrase, a SQL command or malformed data."
by gpvos - Same, I don't use any VPNs though.by zaitsev1393
- Doing a workshop this week on MCP for an enterprise client and explaining the 406 returned by GET against /mcp w/o text/event-stream is exactly one of the things that I have to bring up when I do these.
The specification still leaves a lot to be desired, especially as it relates to auth. There are lots of bad ways to do auth with MCP and only a couple of good ways. It also puts a lot of pressure on the various IdP vendors and relies on lesser used areas of OAuth 2.0/2.1 (like DCR, token exchange, etc.). It started out in a place where the assumption was you were running an MCP Server on a laptop or you were a SaaS provider serving lots of individual users -- somehow DCR in the initial spec iteration seemed like a good idea (spoiler: it wasn't) and fortunately, the latest revision has somewhat addressed that. XAA/ID-JAG & CIMD should continue to round-out some client management and auth solutions for the enterprise.
Gateways are another area that needs to be addressed in the spec. There isn't a formal definition of one in the spec, and yet, there are lots of "gateways" out there. What a gateway is and what it should do is an open question and it means different things to different people depending on who you ask. For example, who does token exchange: the MCP server or the MCP gateway? Both are valid answers right now depending on the implementation or your opinion of which is best.
More spec iterations should be coming this year. I'm still pretty optimistic about MCP as a whole, as it remains a good way to standardize tool calls across agents and some of the other entities that it provides like resources and prompts are genuinely useful to add more determinism to an agent. Interceptors and skills will be good, too.
If you're interested in helping to evolve the spec further, the MCP Contributors Discord is active. There are lots of IGs/WGs that solicit feedback and you can participate in meetings with your feedback.
by eoskx - We build a gateway (MintMCP) and I’d love to connect and exchange notes.
We’re excited about XAA, it will simplify many flows
by jngiam1 - Hey thanks for the note about the discord!
I have also been finding the MCP auth story to be really lacking was excited to see OAuth 2 support until I tried to get it to work at work and realized our idp implementation didn't support 2.1, and went into the spec and started wondering if anyone had a good experience yet. Luckily most of our environment can settle on a OAuth token env var standard until that's all in order.
by kami23 - > Instead, I did something a little bit hacky: if the request is for GET /mcp and the Accept header includes text/html and NOT application/json or text/event-stream, I return a HTML page explaining to the user they're trying to view an mcp server and they need to add it to their client.
This feels like less of a hack and more of discovering what some of the HTTP headers are for. You’re choosing rather reasonably how to present the resource found at /mcp when a client is asking for the resource to be presented in HTML format. It’s perfectly fine to offer an HTML response that says “hey this is not really presentable in HTML. Do this instead.”
by Waterluvian - I thought the same thing, just discovered content negotiation!by RexM
- Indeed! Far from a hack it is the entire purpose to the accept header!by singpolyma3