An MCP server for understanding AWS costs
Hey all - I work at Vantage, a FinOps platform. I know AI is peak hype right now. But it has definitely changed some of our dev workflows already. So we wanted to find a way to let our customers experiment with how they can use AI to make their cloud cost management work more productive. The MCP Server acts as a connector between LLMs (right now only Claude, Cursor support it but ChatGPT and Google Gemini coming soon) and your cost and usage data on Vantage which supports 20+ cloud infra providers including AWS, Datadog, Mongo, etc. (You have to have a Vantage account to use it since it's…
In plain words
This MCP server connects large language models like Claude and Cursor to cloud cost data stored in Vantage, a FinOps platform supporting 20+ infrastructure providers including AWS, Datadog, and MongoDB. Users with a Vantage account can query and analyze their cloud spending through AI conversations, making cost management more efficient. The server enables ad-hoc analysis and other cost optimization workflows, with support for additional models including ChatGPT and Google Gemini planned.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey all - I work at Vantage, a FinOps platform. I know AI is peak hype right now. But it has definitely changed some of our dev workflows already. So we wanted to find a way to let our customers experiment with how they can use AI to make their cloud cost management work more productive. The MCP Server acts as a connector between LLMs (right now only Claude, Cursor support it but ChatGPT and Google Gemini coming soon) and your cost and usage data on Vantage which supports 20+ cloud infra providers including AWS, Datadog, Mongo, etc. (You have to have a Vantage account to use it since it's using the Vantage API) Video demo: https://www.youtube.com/watch?v=n0VP2NlUvRU Repo: https://github.com/vantage-sh/vantage-mcp-server It's really impressive how capable the latest-gen models are with an MCP server and an API. So far we have found it useful for: Ad-Hoc questions: "What's our non-prod cloud spend per engineer if we have 25 engineers" Action plans: "Find unallocated spend and look for clues how it should be tagged" Multi-tool workflows: "Find recent cost spikes that look like they could have come from eng changes and look for GitHub PR's merged around the same time" (using it in combination with the GitHub MCP) Thought I'd share, let me know if you have questions.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
