Thanks for trying us out! Let me know if you run into any issues with deployment or the like. If you want a clean MCP template to get up and running, check out this example: https://github.com/dedalus-labs/brave-search-mcp
Auth is a big one for us, and we're working really hard to provide a robust auth experience that is easy to use for both LLM agents and human users. One of our goals is to help mold the shape that the community takes with MCP. We’ll be launching our auth solution around end of September. I’m personally really excited to tackle this problem.
Thanks! Really glad you noticed this feature. Mixing client-side and server-side tool calls was something we spent a lot of time thinking through.
The current SOTA, e.g. OpenAI’s Responses API or Anthropic’s Computer Use API, basically mandates that server-side tool results return directly, while client-side tool results have to be manually parsed and executed by the user (for obvious security reasons). As a result, it was extremely unclear how a user would be able to chain together tool calls that mixed local and remote tools.
We wanted to close this DX gap, which surprisingly had no real incumbent solution. Users should be able to just define tools and get back clean responses. For power users, we still support manual JSON parsing for full low-level control, but our belief is simple: developers should spend their time building, not doing plumbing work like post-processing tool results.
We tried to keep things simple, so our runner utility class is currently stateless.
However, it's highly extensible, and we can support stateful logic if we wanted to. For instance, we have a cool concept called "Policy" in our SDKs, which is basically a user-defined callback function that is run after each runner step (see our docs for more info). You can build some pretty advanced use cases with this, e.g. executing conditional database calls on a per-step basis.
Good eye. A ~5% surcharge on prepaid credits is the standard model right now for most multi-LLM services. We actually do not use OpenRouter internally, so this number is flexible. One thing I'll note is that we try to be as upfront and transparent about our platform fee as possible so that no one is surprised.
Oh interesting. I've previously looked into implementing it myself but seemed like it would require a lot of effort. I would love to connect and learn more about your implementation. What's the best way to reach out to you? My email is available on my profile.
