TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: An MCP server for understanding AWS costs

119 点作者 StratusBen20 天前
Hey all - I work at Vantage, a FinOps platform.<p>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.<p>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&#x27;s using the Vantage API)<p>Video demo: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=n0VP2NlUvRU" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=n0VP2NlUvRU</a><p>Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;vantage-sh&#x2F;vantage-mcp-server">https:&#x2F;&#x2F;github.com&#x2F;vantage-sh&#x2F;vantage-mcp-server</a><p>It&#x27;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:<p>Ad-Hoc questions: &quot;What&#x27;s our non-prod cloud spend per engineer if we have 25 engineers&quot;<p>Action plans: &quot;Find unallocated spend and look for clues how it should be tagged&quot;<p>Multi-tool workflows: &quot;Find recent cost spikes that look like they could have come from eng changes and look for GitHub PR&#x27;s merged around the same time&quot; (using it in combination with the GitHub MCP)<p>Thought I&#x27;d share, let me know if you have questions.

6 条评论

ponywombat15 天前
AWS have also made their own cost analysis MCP server <a href="https:&#x2F;&#x2F;github.com&#x2F;awslabs&#x2F;mcp&#x2F;tree&#x2F;main&#x2F;src&#x2F;cost-analysis-mcp-server">https:&#x2F;&#x2F;github.com&#x2F;awslabs&#x2F;mcp&#x2F;tree&#x2F;main&#x2F;src&#x2F;cost-analysis-m...</a>
评论 #43842616 未加载
mdaniel15 天前
How does this work? <a href="https:&#x2F;&#x2F;github.com&#x2F;vantage-sh&#x2F;vantage-mcp-server?tab=License-1-ov-file#non-commercial-use">https:&#x2F;&#x2F;github.com&#x2F;vantage-sh&#x2F;vantage-mcp-server?tab=License...</a><p>That is extra weird when thinking about the audience who might be Vantage.sh users (and thus have the ability to create the read-only token mentioned elsewhere) but would almost certainly be using it from their workstation, in a <i>commercial</i> context. Sounds like you&#x27;re trying to keep someone from selling your MCP toy and decided to be cute with the licensing text
评论 #43841075 未加载
评论 #43844049 未加载
_pdp_15 天前
On a related note, I&#x27;m not sure when it became &quot;ok&quot; to leave production credentials scattered across your system in configuration files. So many MCP server examples encourage this pattern, and inevitably, it&#x27;s going to cause trouble at some point.
评论 #43843712 未加载
andrenotgiant20 天前
What&#x27;s the difference between connecting an LLM to the data through Vantage vs directly to the AWS cost and usage API&#x27;s?
评论 #43794674 未加载
cat-whisperer20 天前
This is going to different, as resources end up getting intertwined? or is there a way to standardize it?
salynchnew15 天前
This is dangrous, as I&#x27;ve long held that inscrutible cloud billing was one of the greatest protections we had against a runaway superintelligent AI.<p>Now we only have poor IAM UX to fall back on.<p>&#x2F;s