KlavisAI-Open Source MCP Clients on Slack/Discord AndHosted MCP Servers
Hi HN, I'm excited to share Klavis AI, an open-source project and just released yesterday: https://github.com/Klavis-AI/klavis Why we build Klavis AI: While working with various AI models and external tools, we think MCPs are useful but you need to install and manage them manually. Also there is no tool for integrating them into team workflows on platforms like Slack and Discord. What is it: Klavis provides hosted, Open Source MCP clients on Slack/Discord and hosted various MCP servers. It consists of: - MCP Clients (in the mcp_clients/ directory): We currently…
In plain words
Klavis AI is an open-source project that provides MCP (Model Context Protocol) clients for Slack and Discord, along with hosted MCP servers. It eliminates the need for manual MCP installation and management by integrating them directly into team communication platforms. The platform includes pre-built MCP clients for popular chat services and standalone MCP servers that wrap various tools through a standardized interface, enabling teams to access external capabilities within their existing workflows.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I'm excited to share Klavis AI, an open-source project and just released yesterday: https://github.com/Klavis-AI/klavis Why we build Klavis AI: While working with various AI models and external tools, we think MCPs are useful but you need to install and manage them manually. Also there is no tool for integrating them into team workflows on platforms like Slack and Discord. What is it: Klavis provides hosted, Open Source MCP clients on Slack/Discord and hosted various MCP servers. It consists of: - MCP Clients (in the mcp_clients/ directory): We currently have clients for Slack and Discord bot. - MCP Servers (in the mcp_servers/ directory): These are standalone MCP servers that wrap specific tools or capabilities, exposing them via a standardized MCP interface (specifically, Server-Sent Events). For MCP servers, we have built: - Klavis ReportGen (LLM + Web Search): This is a very cool one. Check out the report generated by the server with a simple query “generate a report about national parks in utah” https://www.klavis.ai/generated-reports/c150d577-ab66-45e4-9... - YouTube video - Document Conversion (via Pandoc) - And we modified various servers to support SSE. How to Try It Out: - We have our hosted version in www.klavis.ai, which has a UI to directly configure MCP clients and servers. - The github repo also has detailed instructions for local development and testing. The basic steps involve setting up a client (Discord or Slack) and running one or more MCP servers (like Report Generation). You can check the readme under mcp_clients and mcp_servers folder for details. - For those of you who do not have much time, check out our launch video: https://www.youtube.com/watch?v=9-QQAhrQWw8 This is an early release, and I'd appreciate feedback from the HN community: - What other tool servers (MCP endpoints) or client platforms would be most valuable? - Any thoughts on improving the developer experience for adding new servers/clients? - Discord for feedback: https://discord.gg/P6fFgv2w We'll be around to answer questions. Thanks for looking!
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 · 27d 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
