Live data from Hacker News

MCP Gateway and Registry

github.com

31–40 of 58 posts

Re: MCP Gateway and Registry

#32
So from what I gather this would be useful at a company level.

Everyone installs this gateway as their only "MCP", then at a central location we can add different MCP tools and everyone automatically gains access to them.

Re: MCP Gateway and Registry

#33

Earlier quoted context omitted.

No, dozens of companies burning money to reinvent the same thing, and the best product rarely wins anyway. You get locked into inferior systems just because they had better timing or marketing. The romantic startup vision sounds nice, but most of those businesses would just fail after wasting capital and talent that could've been used better elsewhere. It's messy and inefficient. >> Or do we just want CorporateSoftTM…

Maybe romantic, that's fair. But I think a world with lots of different choices and options is far better, than one with a single few efficient/optimal solutions. Burning money to reinvent things is fine with me if it trains people up, pays people a salary, creates some original ideas, leads to more choice in the market.

But that's the whole point it never does lead to more choice in the market. Maybe for the year of the hype cycle after that it gets consolidated real quick.

Re: MCP Gateway and Registry

#34
> Caution: The current release (0.6.0) is considered alpha / early beta. It is not production-ready and should only be used for local development, testing, or experimentation. Features, APIs, and behaviors are subject to change without notice. Do not deploy in production environments without thorough security review, validation and additional security mechanisms. Many of the features required for secure, large-scale, or multi-tenant production deployments are still on the project roadmap - which is itself evolving.

IBM posting as if it were a solo open-source developer.

Re: MCP Gateway and Registry

#35

Does anyone use MCP within their product, or is the MCP ecosystem entirely focused on enabling new workflows within an existing chat/agent framework (a la Cursor or Claude code)? Assuming the latter, are there any viable non-developer MCP clients?

Yes, MCPs are just APIs but with a few extra steps and I hope it (or something like it) persists for a long time into the future. If all you want from an Ai assistant is content they scrapped a year ago then you dont need these things, otherwise you need a way to get live data or to take real time actions.

API's, even simple JSON data requests from websites and services were becoming increasing blocked behind cloudflare or hidden as a paid feature, MPC has revived (some of) the open data standards of the internet.

Re: MCP Gateway and Registry

#36

Earlier quoted context omitted.

Maybe romantic, that's fair. But I think a world with lots of different choices and options is far better, than one with a single few efficient/optimal solutions. Burning money to reinvent things is fine with me if it trains people up, pays people a salary, creates some original ideas, leads to more choice in the market.

But that's the whole point it never does lead to more choice in the market. Maybe for the year of the hype cycle after that it gets consolidated real quick.

We could say the same before AI, but I don't think it's true. Ignoring AI for a moment, if I look at databases as an example, there is lots of choice and competition out there:

MySQL, MariaDB, PostgreSQL, TimescaleDB, CockroachDB, YugabyteDB, Teradata, Snowflake, TiDB, SQLite, DuckDB, and more probably.

I think it's led to great choice and a great sharing of ideas. Theres also been a lot of failures too, that's true, but I'm sure some of those failures have led to a few unique features across those products too.

So now with AI, for me it's the same process, just accelerated. Yes, there is lots of junk coming out there, but I think there's lots of good too.

Re: MCP Gateway and Registry

#38

Does anyone use MCP within their product, or is the MCP ecosystem entirely focused on enabling new workflows within an existing chat/agent framework (a la Cursor or Claude code)? Assuming the latter, are there any viable non-developer MCP clients?

We've deployed a few internal MCP servers (e.g. to access our slack messages, salesforce cases and other internal information)

MCP allows to both: - Mount these into your chatbot of choice - Use these in any automation (custom chatbot or other LLM flow) if your framework supports MCP

Tbf I am still under the impression that for the later use case you would rather use the (HTTP) API directly because MCP doesn't allow you to customize the tool descriptions and if you truly want to make your automation perform well you need to iterate on those in my experience.

Re: MCP Gateway and Registry

#39

Earlier quoted context omitted.

But that's the whole point it never does lead to more choice in the market. Maybe for the year of the hype cycle after that it gets consolidated real quick.

We could say the same before AI, but I don't think it's true. Ignoring AI for a moment, if I look at databases as an example, there is lots of choice and competition out there: MySQL, MariaDB, PostgreSQL, TimescaleDB, CockroachDB, YugabyteDB, Teradata, Snowflake, TiDB, SQLite, DuckDB, and more probably. I think it's led to great choice and a great sharing of ideas. Theres also been a lot of failures too, that's true,…

The situation differs when people work within established domains, where the foundational ideas have already been explored. atm everyone does exactly the same some with more salt some with more pepper. Just look back a few months how many of the RAG implementations survived?
Post reply on HN