Toolport
Every tool, one port. One MCP setup for all your AI agents
What it does
A free, open source, local MCP gateway. Set up each server once and every AI agent shares it (Claude, Cursor, VS Code, Codex, and 29 more). Instead of dumping every tool definition into context, it exposes a few meta-tools your agent searches on demand. Benchmarked and graded for correct answers, that's up to 91% fewer tokens at the same task success. Secrets live in your OS keychain, not client configs. Rug-pulls and tool poisoning get flagged, and destructive calls can wait for your approval.
A free, open source local MCP gateway. Set up each server once and every AI agent shares it (Claude, Cursor, VS Code, Codex), with up to 91% fewer tool tokens, secrets in your OS keychain, and one set of agent rules applied everywhere.
Set up your MCP servers once and share them across Claude, Cursor, Codex, and your other AI clients. Tools load on demand to keep context small. Your keys stay on your machine. Tool definitions, counted in tokens, load on every request before you've typed a word. Fewer tokens mean sharper answers, more headroom under your plan's limits, and lower bills. Those are tool-definition tokens on one request. Graded at the same task success, Toolport uses 74 to 91% fewer across servers · reproduce the benchmark Stop pasting the same server config and API key into Claude, then Cursor, then Codex. Set up and authenticate a server once in Toolport and it shows up in every agent, with hot toggles and…from toolport.app
Does the same job
all alternatives →
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 · 16d 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 · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com