This looks interesting, and congrats on the launch. An immediate piece of critical feedback is that you should try to be a little more specific in the tagline. All MCP servers give context to coding agents - that's what an MCP server is (at least the resources/prompts channels of an MCP server).
Sometimes Claude code defaults to using the older versions of certain libraries, have to explicitly tell claude to use the specific version. Even then it goes back to older version, so I downloaded the entire repo of that library and put it in my project folder. Does your product solve that ?
I was unable to locate details regarding how the code/data is used/owned by the service. Clicking on the Legal link simply sends you to the top of the Home Page.
At this time I can't even think about using the tool until I know what you are doing with my information and who owns or has access to it.
> In internal evals we improved Cursor’s performance by 27 % once Nia had indexed external docs models couldn’t get from their training data or searching the web.
What external docs do you have access to that aren't found on the web?
When I start a nontrivial coding task with AI, I added a “context” directory, instructions in the tool prompts how to use the files in that directory, and then I spent a couple hours using a thinking chat AI to generate the documentation I wanted (like “build me an API document for this library, the source code is at this URL and here are some URLs with good example code).
I’ve had generally good results with this approach (I’m on project #3 using this method).
I do this for larger requests I make, however I find large requests end up giving me nonsense due to the amount of context 10 odd relevant files + design context.
I'm just using vscode edit mode, so I expect I'm being too simple, mostly as I haven't found out how to make agent mode work with front and back end in separate docker containers.
Would you mind sharing a bit of insight into how you've configured your environment such that you get good results?
A killer app would be a up-to-date database of documentation from X amount of sources. For example, fully up to date Shopify API Documentation which could be included within cursor at the click of a button.
I believe right now you're requiring us to do the scraping/adding?
I’ve been following you on X since your account was randomly shown to me. Your story is really cool, but also is your product. I’m working on my own LLM context problem as a side project (in a completely different space), but this could really fill voids I’m finding when doing it myself.
I’m going to try this today. Best of luck with this!
Are you still building this yourself (and Claude)?
not sure what I am paying for here. isn't the idea of MCP is self-deployed MCP servers? I have my data, my hardware, I pay for LLM, and then also pay for this?... cmon.
I've been using GitMCP.io + Github Copilot for this problem specifically (AI assistant + accurate docs). The downside is that you need to add a separate MCP server for each repository, but the qualitative difference in agent mode is incomparable.
I used it recently to do a major refactor and upgrade to MLFlow version 3.0. Their documentation is a horrid mess right now, but the MCP server made it a breeze because i could just query the assistant to browse their codebase. Would have taken me hours extra myself.
Context7 injects a huge amount of tokens into your context, which leads to a very low signal/noise ratio. I’m using https://ref.tools myself, it delivers much more targeted docs.
The idea is nice but pricing for it might be so hard to land. You're proposal is that I have to pay $20/mo for a Cursor licence which includes an IDE, coding agent and all the shenanigans involved to make it work and then on top of that I have to spare an additional $15/mo to have access to up-to-date documentation. That might be hard selling them side by side.
At some point we will need an aggregator of MCPs to be delivered with the agents, the perceived cost of shopping for them individually is not worth the cost from the consumer perspective.
28 comments
[ 3.1 ms ] story [ 55.5 ms ] threadAt this time I can't even think about using the tool until I know what you are doing with my information and who owns or has access to it.
What external docs do you have access to that aren't found on the web?
I’ve had generally good results with this approach (I’m on project #3 using this method).
I'm just using vscode edit mode, so I expect I'm being too simple, mostly as I haven't found out how to make agent mode work with front and back end in separate docker containers.
Would you mind sharing a bit of insight into how you've configured your environment such that you get good results?
I believe right now you're requiring us to do the scraping/adding?
I’m going to try this today. Best of luck with this!
Are you still building this yourself (and Claude)?
I used it recently to do a major refactor and upgrade to MLFlow version 3.0. Their documentation is a horrid mess right now, but the MCP server made it a breeze because i could just query the assistant to browse their codebase. Would have taken me hours extra myself.
and can you explain more on how you use the "entire codebase"?
At some point we will need an aggregator of MCPs to be delivered with the agents, the perceived cost of shopping for them individually is not worth the cost from the consumer perspective.