←back to thread

133 points wirehack | 2 comments | | HN request time: 0.404s | source

Hey HN! We are Klavis AI (https://www.klavis.ai/) 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.

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.

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:

Github query: "Find my stale pull requests in our main repo"

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.

Jira query: "Create a bug ticket in the 'MOBILE' project about the app crashing on startup."

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.

Slack query: "Post a message in the #announcements channel that bonus will be paid out next Friday."

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.

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.

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.

On the MCPMark https://mcpmark.ai/leaderboard/mcp, 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.

Here is a quick demo to watch Strata navigate a complex workflow with multiple apps, automatically selecting the right tools at each step: https://www.youtube.com/watch?v=N00cY9Ov_fM.

You can connect to any external MCP Server into Strata, and we have an open source version for it: https://github.com/Klavis-AI/klavis.

For team or production use with more features, visit our website: https://www.klavis.ai. 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.

We look forward to your comments. Thanks for reading!

Show context
saberience ◴[] No.45361825[source]
This is a solution seeking a problem. Why would we want a single reliable agent to have access to 1000s of tools? When would this ACTUALLY be valuable or useful.

What IS useful and offers value is having an agent which accesses 1 or 2 tools but always uses those tools accurately and correctly 99.9+% of the time.

I've seen tons of MCP companies who are offering 1000s of wrapped HTTP APIs as MCP tools, which is note very easy to implement, but in reality, it's totally fucking useless for enterprise use-cases which need to work reliably, in a secure, repeatable fashion.

Any chump can rig an MCP client to 20 tools, but then watch your agent fail again and again and again.

Basically, this is a bad idea for a business and I'd personally suggest pivoting to something that focuses on ensuring a single agent works reliably, provides guardrails, evaluation, security etc. This is the real challenge to solve.

replies(1): >>45363045 #
1. klauslin666 ◴[] No.45363045[source]
I'd say the value of Strata is more than just one MCP Server, it's a strategy that can apply on AI Agent interacting with tools or even other AI agents.

in your example, one agent access 1~2 tools, what if an enterprise have 1000 use cases and need 1000 AI agents as you said. How you let your system intelligently dispatch the correct AI agent to the correct use case? (or will OpenAI create 1000 customGPT and let user to choose which one? ) instead you need a way to intelligently dispatch user query to different sub-tools or sub-agent, depends on how you design. But the essence of Strata I believe is rely on model's reasoning to minimize context window + maximizer relevant info. and then solve the user query.

Security is another level of topic and I think it's not related to this approach.

replies(1): >>45386446 #
2. saberience ◴[] No.45386446[source]
The reality is that enterprises don't need 1000s of tools. I've worked for enterprises, and I've also been involved heavily with horizontal and vertical agent platforms.

The idea of 20000 MCP tools sounds good on paper, but the reality is that the enterprise wants an agent that just connects to Jira and ServiceNow and actually works. They don't care about 1000 randomly shitty MCP servers built by random people online which they can't trust.