wirehack

Try https://www.klavis.ai, which is a open source MCP integration platform. (I am one of the co-founders)

Yes, submit a PR there and we will merge it if the quality of your server is good and we think it will be helpful to our communities. You can read our contributing guide for more detail: https://github.com/Klavis-AI/klavis/blob/main/CONTRIBUTING.m....

No this is pure coincidence lol.

Strata supports connecting to custom external MCP servers via API: https://docs.klavis.ai/api-reference/strata/create. For the servers on our website, most of them are created by ourselves.

We build our MCP servers ourselves and many of them are open source. You can check out our github repo.

Their findings on KV-cache invalidation are spot on for a single-context approach.

Strata's architecture is philosophically different. Instead of loading a large toolset and masking it, we guide the LLM through a multi-step dialogue. Each step (e.g., choosing an app, then a category) is a separate, very small, and cheap LLM call.

So, we trade one massive prompt for a few tiny ones. This avoids the KV-cache issue because the context for each decision is minimal, and it prevents model confusion because the agent only ever sees the tools relevant to its current step. It's a different path to the same goal: making the agent smarter by not overwhelming it. Thanks for the great link!

Thank you! I did not know this trick! I am fixing this now.

1. Yes I agree. To be honest we are a young company (as you can tell we are from YC X25), so we are still figuring out the pricing. But thank you for the feedback and sharing your thoughts.

2. Yes the idea is not complex once you understand it. But there are some nuances we found along the way and supporting more integrations are always important but requires engineering efforts. Thank you!

We do not build the MCP clients, but for many of the clients I believe it is hard-coded into the deterministic client code.

Thank you!

Yeah I see what you mean. Many MCP clients has the ability to ask human for confirmation before a tool call is executed. In this way, you can check the tool call before it executes.

1. Sure, we will clarify that in the pricing page, thank you! As you can see from our evaluation, we are much better than official MCP servers. I think people care more about getting things done correctly. Otherwise, you waste all the model tokens for nothing. We do have enterprise deals where we can work out a customized pricing plan for your specific use case. Come talk to us if you are interested.

2. One VERY important distinction is that the model is doing the "search" here, not some RAG algorithm or vector database. Therefore, as the model becomes smarter, this approach will be more accurate as well.

We also provide an open-source version for Strata so that you can have full control. You can self-host it on your own infrastructure, so your credentials never have to touch our servers.

1. Hi! We noticed this for Strata as well so we are ONLY counting the execute_action in Strata. This means the fee is the same as using the traditional, flat approaches. In other words, the 3 previous calls does not cost you anything!

2. I think the main drawback of search method is like giving a human lots of tools/APIs but you can ONLY access them via a search interface. This feels weird and should be improved. For our approaches, the step by step methods allow you to see what categories/actions are available. We also provide a documentation search so that you get the best out of both worlds.

We are SOC2 compliant. So this will not be a problem. Come talk to us if you are interested in using this for your clients and we can work out the details.

Yes there is a way to impose a static allowlist. As a very simple example, you can disable certain servers completely via the UI or the API.

We are aware of this and working on it now. We are actually code complete on Microsoft Teams and Outlook. We will definitely launch it within the next week or so.

Thank you! Yes we do provide auth and support other remote MCP servers via our API : https://docs.klavis.ai/api-reference/strata/create. It indeed support custom headers. Feel free to give us a try or come talk to us!

We tested our approaches with several thousand tools and it is working pretty well. Also we provide API access as well, so any developer can use this, not just on Microsoft or VS Code.

The eval benchmark also compared Notion and we are 13% higher than them as well!

That's the critical question. The key is that Strata never exposes all tools to the agent at once. Our progressive guidance acts as a dynamic allowlist, so that the agent only "sees" the specific tools relevant to its immediate task. This fundamentally reduces the blast radius at each step. We do provide a comprehensive audit trails for every action, giving a CISO a centralized control plane to manage and monitor agent capabilities, rather than an exponential risk. If you are interested, come talk to us!

Oh yes for sure. Checkout https://www.klavis.ai/mcp-servers. You do not need to sign up. But you cannot see the auth flow for obvious reasons.

Yes we do! Just signup to our website https://www.klavis.ai/home/mcp-servers and you will see all the apps and the auth options.

Yes it is the former. The value comes from its progressive guidance during a task, not just in the initial setup.

As for latency, we optimized for that. For examples, Strata automatically uses a direct, flat approach for simple cases. And we use less tokens compared to official MCP servers as well, as shown in the benchmark.

Haha yeah we did optimize it a lot before the launch!

Actually for us, our first prototype was pretty good! We are also surprised about that because it took us a day or so to build the the prototype (only for one integrations though). Then it took us another week to build another prototype for multiple integrations.

Glad it could be helpful to you! Curious what AI agents you are building and exactly what tools caused the failure.

In any case, feel free to give us a try!

As you can see from our examples, the main approach is not tool search. Instead, Strata guides your AI agent step by step, going from server to categories to actions to action details so that the model does not get overloaded. We actually have 1000+ tools for some of the integrations (e.g. GitHub) and this approach works better than traditional methods.

Think of it as a search engine vs. a file explorer. But we do provide documentation search as well. So you get the best out of the two worlds.

haha I like the word vibefrastructure!

Yes thank you for sharing your thoughts. The MCP interfaces definitely sound promising. However I think it does not stop people from building other MCP servers . And different people may have different opinions regarding how to design this interface for a search MCP server.

TBH I think all of these problems are still very new (remember MCP is only 6 months old) and I think we need to wait and see how things evolve.

Hopefully, in the end we will all converge to the real standards. But I understand your concerns now and I agree that right now it is a bit messy.