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: Gomcptest – A Go toolkit for testing LLM agents (MCP) with VertexAI

2 点作者 owulveryck2 个月前
I built a Go toolkit that helps test and interact with Model-Calling-Protocol (MCP) tools, primarily for developing and understanding agentic systems. It currently works with Google&#x27;s VertexAI SDK.<p>What it does:<p>- Provides a basic set of tools for testing MCP implementations<p>- Includes a CLI that emulates Claude Code functionality<p>- Offers an OpenAI API v1 compatible server (with some limitations)<p>Try it yourself:<p>1. Clone the repo: `git clone <a href="https:&#x2F;&#x2F;github.com&#x2F;owulveryck&#x2F;gomcptest" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;owulveryck&#x2F;gomcptest</a>`<p>2. You&#x27;ll need a Google Cloud Platform account with VertexAI API enabled<p>3. Follow the setup instructions in the README<p>This is strictly a proof of concept for learning purposes - I built it to better understand how agentic systems work and to have a simple way to develop and test various tools.<p>I&#x27;m especially interested in feedback on:<p>- Any use case you think it can enable<p>- Ideas for additional tools that would be

暂无评论

暂无评论