Launch HN: Strata (YC X25) – Strata 发布：一个 AI 多计算平台服务器，可同时处理数千种工具
3 分•作者: wirehack•8 个月前
嘿，HN！我们是 Klavis AI (<a href="https://www.klavis.ai/">https://www.klavis.ai/</a>)，我们正在推出 Strata，一个开源的 MCP 服务器，帮助 AI 智能体使用成千上万的 API 工具，而不会不堪重负。Strata 不会一次性展示所有可用工具，而是根据 AI 的实际需求逐步揭示它们。<p>作为前 Google Gemini 工具使用团队的高级软件工程师，我亲眼目睹了 AI 在使用工具时遇到的困难。如果你构建过 AI 智能体，你可能也遇到过同样的问题：（1）AI 智能体难以从数百个选项中选择正确的 API。（2）工具描述和信息会消耗大量的 token 预算。（3）大多数服务器限制在 40~50 个工具，以避免这些问题，这限制了你能构建的内容。<p>Strata 没有一开始就用所有东西淹没 AI，而是像人类一样工作。它引导 AI 智能体发现相关类别，然后列出这些类别中可用的操作。它依赖 LLM 的推理能力，逐步深入，找到所需的精确工具。以下是一些例子：<p><i>Github 查询：“在我们的主仓库中找到我过期的 pull request”</i><p>Strata：AI 模型识别出 GitHub → 显示类别（仓库、问题、PR、操作）→ AI 选择 PR → 显示 PR 专用操作 -> AI 选择 list_pull_requests → 显示 list_pull_requests 详情 -> 使用正确的参数执行 list_pull_requests。<p><i>Jira 查询：“在 'MOBILE' 项目中创建一个关于应用程序启动时崩溃的 bug 票。”</i><p>Strata：AI 识别出 Jira → 显示类别（项目、问题、Sprint）→ AI 选择问题 → 显示操作（create_issue, get_issue）→ AI 选择 create_issue → 显示 create_issue 详情 → 使用正确的参数执行。|<p><i>Slack 查询：“在 #announcements 频道中发布一条消息，说明下周五将支付奖金。”</i><p>Strata：AI 识别出 Slack → 显示类别（频道、消息、用户）→ AI 选择消息 → 显示操作（send_message, schedule_message）→ AI 选择 send_message → 显示 send_message 详情 → 使用正确的参数执行。<p>这种渐进式方法释放了一个巨大的优势：深度。虽然大多数集成只提供少数高级工具，但 Strata 可以为 GitHub、Jira 等单个应用程序公开数百个细粒度的功能。你的 AI 智能体最终可以访问真实工作流程所需的深度、特定功能，而不会迷失在选项的海洋中。<p>在幕后，Strata 管理身份验证 token，并包含一个内置的搜索工具，供智能体在遇到问题时深入研究文档。<p>在 MCPMark <a href="https://mcpmark.ai/leaderboard/mcp" rel="nofollow">https://mcpmark.ai/leaderboard/mcp</a> 上，Strata 的 pass@1 率比官方 GitHub 服务器高出 +15.2%，比官方 Notion 服务器高出 +13.4%。在人工评估测试中，它在复杂、真实的多应用程序工作流程中达到了 83% 以上的准确率。<p>这是一个快速演示，观看 Strata 导航一个包含多个应用程序的复杂工作流程，并自动在每个步骤中选择正确的工具：<a href="https://www.youtube.com/watch?v=N00cY9Ov_fM" rel="nofollow">https://www.youtube.com/watch?v=N00cY9Ov_fM</a>。<p>你可以将任何外部 MCP 服务器连接到 Strata，我们有一个开源版本：<a href="https://github.com/Klavis-AI/klavis" rel="nofollow">https://github.com/Klavis-AI/klavis</a>。<p>对于团队或生产使用，以及更多功能，请访问我们的网站：<a href="https://www.klavis.ai">https://www.klavis.ai</a>。一键将 Strata 添加到 Cursor、VS Code 或任何兼容 MCP 的应用程序中。你也可以使用我们的 API 轻松地将 Strata 插入到你的 AI 应用程序中。<p>我们期待你的评论。感谢阅读！
查看原文
Hey HN! We are Klavis AI (<a href="https://www.klavis.ai/">https://www.klavis.ai/</a>) and we're launching Strata, one open-source MCP server that helps AI agents use thousands of API tools without getting overwhelmed. Instead of showing all available tools at once, Strata reveals them step-by-step based on what the AI actually needs.<p>As a former Senior SWE on Google Gemini 's tool use team, I saw firsthand how AI would struggle with tools. If you've built AI agents, you've likely hit the same walls: (1) AI agents struggle to pick the right API from hundreds of options. (2) Tool descriptions and info consume massive token budgets. (3) Most servers cap at 40~50 tools to avoid these problems, limiting what you can build.<p>Instead of flooding the AI with everything upfront, Strata works like a human would. It guides the AI agents to discover relevant categories, then lists available actions in those categories. It relies on LLMs’ reasoning to drill down progressively to find the exact tool needed. Here are some examples:<p><i>Github query: "Find my stale pull requests in our main repo"</i><p>Strata: AI model identifies GitHub → Shows categories (Repos, Issues, PRs, Actions) → AI selects PRs → Shows PR-specific actions -> AI selects list_pull_requests → Shows list_pull_requests details -> Executes list_pull_requests with the right parameters.<p><i>Jira query: "Create a bug ticket in the 'MOBILE' project about the app crashing on startup."</i><p>Strata: AI identifies Jira → Shows categories (Projects, Issues, Sprints) → AI selects Issues → Shows actions (create_issue, get_issue) → AI selects create_issue → Shows create_issue details → Executes with correct parameters.|<p><i>Slack query: "Post a message in the #announcements channel that bonus will be paid out next Friday."</i><p>Strata: AI identifies Slack → Shows categories (Channels, Messages, Users) → AI selects Messages → Shows actions (send_message, schedule_message) → AI selects send_message → Shows send_message details → Executes with correct parameters.<p>This progressive approach unlocks a huge advantage: depth. While most integrations offer a handful of high-level tools, Strata can expose hundreds of granular features for a single app like GitHub, Jira, etc. Your AI agent can finally access the deep, specific features that real workflows require, without getting lost in a sea of options.<p>Under the hood, Strata manages authentication tokens and includes a built-in search tool for the agent to dig into documentation if it gets stuck.<p>On the MCPMark <a href="https://mcpmark.ai/leaderboard/mcp" rel="nofollow">https://mcpmark.ai/leaderboard/mcp</a>, Strata achieves +15.2% higher pass@1 rate vs the official GitHub server and +13.4% higher pass@1 rate vs the official Notion server. In human eval tests, it hits 83%+ accuracy on complex, real-world multi-app workflows.<p>Here is a quick demo to watch Strata navigate a complex workflow with multiple apps, automatically selecting the right tools at each step: <a href="https://www.youtube.com/watch?v=N00cY9Ov_fM" rel="nofollow">https://www.youtube.com/watch?v=N00cY9Ov_fM</a>.<p>You can connect to any external MCP Server into Strata, and we have an open source version for it: <a href="https://github.com/Klavis-AI/klavis" rel="nofollow">https://github.com/Klavis-AI/klavis</a>.<p>For team or production use with more features, visit our website: <a href="https://www.klavis.ai">https://www.klavis.ai</a>. Add Strata to Cursor, VS Code or any MCP-compatible application with one click. You can also use our API to easily plug in Strata to your AI application.<p>We look forward to your comments. Thanks for reading!