Hypagon Gateway MCP server
Commit Nov 14, 2026A self-hosted Chromium browser that allows AI agents to navigate the web, interact with elements, and maintain persistent memory via MCP.
Also known as hyperbolictonic/hypagon
- Stars
- 2
- Tools
- 17
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- MIT
What is Hypagon Gateway MCP?
Hypagon Gateway is a self-hosted Chromium browser that allows AI agents to navigate the web, interact with elements, and maintain persistent memory via MCP. It exposes 17 tools, such as navigate, observe, find.
Summary generated from the project's README
About Hypagon Gateway MCP server
Hypagon Gateway provides a visible, stateful Chromium browser that AI agents can drive directly from your machine. Unlike cloud-based browser services or headless libraries, this is a desktop application that runs a real Chromium window with hardware acceleration, persistent cookies, and multi-tab support. It operates via the Model Context Protocol using stdio or a localhost bridge, allowing it to integrate with any MCP-compatible client like Claude Desktop or Cursor.
Developers can use it to give agents human-like interaction capabilities, including focus-independent input that uses Bézier paths and Gaussian typing. The server includes a local LanceDB called Cortex for semantic memory, a session cookie vault, and a script vault to ensure tasks can resume where they left off. It offers a variety of tools for observing pages through markdown or accessibility trees, taking screenshots, and interacting with web elements without requiring a cloud account or external API keys.
What you can do with it
- 1Autonomous web navigationAn AI agent can navigate websites, click elements, and fill out forms using human-like input patterns.
- 2Persistent web researchAn agent can perform long-running research tasks that maintain state and memory across different sessions.
- 3Token-efficient page readingAn AI can extract structured information from a webpage using markdown instead of expensive screenshots.
- 4Background web automationA developer can run browser automation tasks in the background while continuing to work in other applications.
Written from the project's README. Every use case is checked against a quote from it.
Hypagon Gateway MCP tools 17
Detected from the READMEnavigateobservefindactwait_forextractcaptureevaluate_javascriptdevtoolshuman_in_loopcollaboratebrowser_workspace
Show all 17 toolsShow fewer tools
mediashadow_iframesresearchmemoryhelp
Configuration
ELECTRON_RUN_AS_NODEHB_WRAP_TOKEN_FILE
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablehyperbolictonic/hypagon is public and reachablegithub.com/hyperbolictonic/hypagon ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-10github.com/hyperbolictonic/hypagon ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model17 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub⚡ Hypagon Gateway
The local browser for AI agents.
"I'll hack the Gibson"
— Dade Murphy (AKA Crash Override), Circa 1995
🧭 Index
- About — What it is · A punk-ethos alternative to browser clouds
- The deck — Theme & Cyberdeck UI · Ghost cursor telemetry · Focus-independent input · Multi-tab browsing
- Reading the web — Orthogonal primitive layer · Construct harvester · JEV page compaction · Set-of-Marks
- Driving the web — Shield-breaker · Form filler · Human-in-the-loop
- Memory & data — Cortex · Downloads · Media download integration · Session vault · Script vault · Timelapse recorder
- Inspection — Network & API streams · WebSocket & SSE
- Operating it — System tray · MCP tools (16 advertised · +2 decision · +3 JEV) · Agent skills · REST wrappers
- Building on it — Architecture lowdown · Codebase & docs · Quickstart · Testing · OKF knowledge
- Optional decision layer —
decide/drivedesign notes · Control layer: targeting, consent, human takeover · Shadow DOM & iframes: what Hypagon Gateway can see and click · Shadow Walk: sealed-content plan · Field notes from dogfooding · Changelog - Release notes — What shipped · All releases
- Lore — Neuromancer inspiration
🕶️ What it is
Hypagon Gateway is a visible, stateful web browser that any MCP agent can drive.
Most agent browsers are a library you integrate, or a cloud you rent. Hypagon Gateway is a desktop application you own: a real Chromium window on your machine, controlled over the Model Context Protocol. Your agent runs where you already run it — local or remote — and Hypagon Gateway supplies the browser, the input, and the memory.
- A real browser, not a simulation. Visible Chromium with hardware acceleration, persistent cookies, real tabs, downloads, and a human-sized viewport. No headless fingerprint.
- Structured first, pixels when needed.
observereturns a compact, addressable view of the page (markdown, text, accessibility tree, or Set-of-Marks).take_screenshotis there when layout matters. - Input that looks human. Clicks and keys travel over the Chrome DevTools Protocol with Bézier paths and Gaussian typing cadence — and they land even when another application owns the foreground.
- State that survives. LanceDB memory, bookmark and session vaults, download harvesting and a script vault mean the next session starts where the last one stopped.
- Self-hosted by construction.
stdioMCP plus a localhost bridge. No account, no dashboard, and no telemetry leaving the machine.

Recorded from the running app: Google → “hypagon definition” → AI Mode. Open the MP4 if your browser does not animate WebP.
[!WARNING] EXPERIMENTAL PROTOTYPE: Hypagon Gateway is currently under active, experimental development. Tool contracts, telemetry tuning, and database schemas may evolve rapidly. Built for developers experimenting with multimodal local AI agents.
[!IMPORTANT] RESEARCH PURPOSES ONLY: This software is provided strictly for educational, testing, and local AI agent research purposes. It is not intended for malicious use, automated credential stuffing, unauthorized exploitation, or violating third-party websites' Terms of Service. Users are responsible for complying with all applicable laws and terms.
Installers: grab them from Releases — Windows Setup/Portable/zip, macOS dmg/zip (x64 + arm64), Linux AppImage/deb/tar.gz. macOS is unsigned for now: right-click → Open (or xattr -dr com.apple.quarantine "/Applications/Hypagon Gateway.app"). Built by GitHub Actions; see docs/BUILDING.md.
🤘 A Punk-Ethos, DIY Alternative to browser-use, Playwright Agents & Hosted Browser Clouds
Most "AI browser" tooling today is a library you integrate, or a cloud you rent. browser-use is a popular MIT-licensed Python framework that drives Playwright with its own agent loop (plus an optional hosted cloud); Playwright / Puppeteer / Selenium are general-purpose drivers where you write the loop; and managed browser clouds run a remote Chromium and bill per session. They're good tools — this isn't a rivalry, it's a different shape.
Hypagon Gateway is the other road: a single, self-hosted desktop app you own (Electron, no account, no dashboard). It runs a real, visible Chromium on your own machine and speaks MCP over stdio (+ a localhost bridge), so it drops into whatever agent runner and whichever model you already use — local or remote, with no cloud account, no API key, no seat pricing, and no telemetry leaving your box.
That's the punk ethos: one operator, one machine, a tool you can read, fork and keep. Built by one person, not a company. No VC, no roadmap-by-committee, no dashboard.
How it differs, honestly
browser-use (Python / Playwright) |
Playwright · Puppeteer agents | Hosted browser clouds | Hypagon Gateway | |
|---|---|---|---|---|
| Shape | Library with its own agent loop | Driver — you write the loop | Managed remote browser | MCP server any MCP client can call |
| Browser | Playwright Chromium (often headless) | Playwright / Puppeteer | Remote Chromium | Visible Chromium (headless: false) in an Electron chassis |
| Where it runs | Your machine, or their cloud | Your machine / your CI | Their datacentre | Your machine, always — local-first |
| Model | Bring your own (usually a cloud LLM) | Bring your own | Bring your own | Bring your own — local or remote |
| Input | Playwright-driven events | Playwright-driven events | CDP over the wire | Focus-independent CDP input + Bézier ghost cursor + Gaussian typing (isTrusted: true) |
| Memory | Framework-level, BYO store | none | Their store | Local LanceDB "Cortex" — semantic recall of everything it harvests |
| Cost | MIT + your LLM (+ optional cloud) | Free + your LLM | Per-session billing | MIT. No cloud, no metering, no telemetry. |
What that buys you in practice
- Self-hosted and local-first. The browser, the memory, the logs and the model all stay on the box.
- Built for a machine you're also using. Input goes over CDP and is focus-independent — clicks and typing land while your editor owns the foreground — and occluded windows keep hydrating and scrolling, so long harvests keep running behind your other apps.
- Tier-graded tool surface, not a token bonfire. Reading is
observe(as:"markdown")with inline[#id]marks (no screenshot tax); interaction is oneact;[TIER 1/2/3]prefixes plus atools/recommendedresource tell the agent what to prefer. - Honest about its limits. Detached reads are gated,
evaluate_javascriptis "use deliberately" rather than banned, and failures are machine-coded (STALE_REF,TIMEOUT,NO_TARGET,BAD_REQUEST,NOT_SUPPORTED) instead of vibes. - No framework lock-in. Because the interface is MCP, your runner stays yours: swap the agent, swap the model, keep the tool.
New here? Plain-English FAQ
What is this, in one sentence? A web browser that an AI can drive for you: it opens real pages, reads them, clicks, types, fills in forms, and remembers what it found.
Is it a browser I use myself? It's a real browser window. You can watch it, and you can take over at any time — most people just let their AI do the driving.
Do I need to be a programmer? To use it with an AI assistant you already have: no — you paste one line of configuration into that assistant. To change how it behaves internally: yes, it's a code project.
What's an "MCP server", in plain terms? MCP is a standard plug shape for AI tools. If your AI app accepts MCP plugins, it can use this one. Claude Desktop, Cursor and several other apps speak it.
Can I install an agent skill too?
Yes. The hb-browser and hb-wrap skills are at skills/.
hermes skills install https://raw.githubusercontent.com/hyperbolictonic/hypagon/main/skills/hb-browser/SKILL.md
hermes skills install https://raw.githubusercontent.com/hyperbolictonic/hypagon/main/skills/hb-wrap/SKILL.md
npx skills add hyperbolictonic/hypagon --skill hb-browser
npx skills add hyperbolictonic/hypagon --skill hb-wrap
Add -g -y to the npx commands for a non-interactive global install.
Which AI can drive it? Any assistant that supports MCP — a cloud service, or a model running on your own computer. You choose, and you aren't locked to one provider.
Do I need to pay for anything? No subscription and no account. The software is free and open source. The only cost is whatever you already pay for your AI, if anything.
Where does my data go? Nowhere. The pages it reads, the notes it keeps and the logs all stay on your computer. There's no company server in the middle and no usage tracking.
Could a website tell it's a bot? It's built to be hard to spot: a normal visible browser, mouse movement and typing that look human, and it clears cookie banners politely. Nothing is unbeatable, but it isn't the obvious "automated script" that gets blocked.
What happens at a CAPTCHA? It doesn't solve them. It asks you to step in (it can send a notification and bring the window forward), then continues once you're done.
Does it run headless on a server? Not really, and that's on purpose. It runs a visible browser on a normal desktop, which is exactly why it looks human. For large-scale server-side scraping, a different tool fits better.
Is using it allowed? It's for personal research and testing. You still have to follow each website's rules and the law — running it yourself doesn't change that. Don't use it to break into accounts or ignore terms of service.
What do I need to run it? A normal Windows desktop (that's the tested target). If your computer can run a browser and an AI assistant, it can run this.
Is it finished? No. It's an experimental project by one developer — expect rough edges and things that change.
FAQ for developers — browsers, memory, and the tricky bits
Is there a self-hosted, open-source alternative to browser-use?
Yes — MIT-licensed and entirely local. But note the shape: this is a tool surface, not an agent framework. If you want a Python framework that owns the loop, browser-use is the right tool; if you want a self-hosted browser that your own agent drives, this is it.
Can I use it with Claude Desktop, Cursor, or a local LLM?
Yes. It's an MCP server, so any MCP client works - point your client at bin/mcp-server.cjs and the hb-browser tool namespace appears (legacy kuang alias still works).
Does it need a cloud account, API key, or per-session billing?
No. There is no cloud tier. The only network calls are the ones your agent makes to the pages it visits (plus, optionally, a search engine via search_web).
Is it headless? Deliberately the opposite. It runs a visible Chromium so a human can watch, take over at a CAPTCHA, and so the session stays an honest, real browser. Headless-at-scale scraping is a different job; this is a single operator's console.
Will Cloudflare block it like Puppeteer / Playwright?
It's built for exactly that fight: real CDP input with isTrusted: true, cubic Bézier pointer kinematics, Gaussian typing cadence, a genuine cookie jar, and an autonomous consent-modal breaker. No promises — anti-bot is an arms race — but it is not naive headless emulation.
Can I point it at my existing Playwright test suite? No. This isn't a test driver; Playwright remains excellent for deterministic suites. Grade Eleven is an agent-facing browser an LLM operates.
Where does memory live? Locally, in LanceDB ("Cortex"): harvested pages and vaulted scripts are embedded and semantically recallable, so your agent keeps research context across sessions without a hosted vector store.
Is it production-ready? No — it's an experimental prototype for local AI research. That's rather the point.
Punk ethos, not carte blanche. Owning your tooling doesn't change the law: the RESEARCH PURPOSES ONLY terms at the top of this README still apply. The point is ownership and readability, not immunity.
🎯 Core Architecture Principles
- 100% Real Browser Chassis: No headless emulation, synthetic user-agent spoofing, or sandboxed scraping. Hypagon Browser runs a full-fledged, visible Chromium instance (
headless: false) with hardware acceleration, audio/video capabilities, and authentic cookie/session persistence. - Multimodal Vision Integration: Specifically tailored for multimodal models (e.g. Bonsai 2 27B). The agent takes high-res viewport screenshots (
take_screenshot) to visually understand layouts, buttons, and dynamic canvas states, and can act directly by coordinate, selector, or mark badge (act). - Full Developer Console & Script Execution: Gives the agent full console access (
get_console_logs) to inspect runtime errors and API output, plus arbitrary JavaScript evaluation (evaluate_javascript) to interact with complex SPAs. - Behavioral Bot Detection Bypass: Bypasses Cloudflare, Akamai, Datadome, and behavioral bot sensors by avoiding synthetic
element.click()events (isTrusted: false). Instead, it dispatches real input events over the Chrome DevTools Protocol (Input.dispatchMouseEvent/Input.dispatchKeyEvent/mouseWheel) accompanied by organic cubic Bézier pointer movement and human Gaussian typing cadence. CDP delivery is focus-independent — it lands even when another application owns the OS foreground — withwebContents.sendInputEventkept only as a fallback.
🎨 Theme & Cyberdeck Interface
Built with Tailwind CSS v4 and DaisyUI 5:
- Custom Theme:
mark-eleven - Color Inspiration: Antigravity electric cyan (
oklch(75% 0.18 215)), VS Code workspace slate (oklch(21% 0.012 250)), and Photoshop deep charcoal neutrals. - DaisyUI Components:
navbar&mockup-browseraddress bar with real-time navigation and SSL/protocol status.statusandbadgeindicators reflecting live agent lifecycle (IDLE,TRAVERSING,SIMULATING_INPUT,HARVESTING).tabs(tabs-border) for switching between Telemetry Kinematics, Construct Terminal, and MCP Matrix Logs.stats/statblocks tracking coordinates, Bézier velocity, tokens saved, and interaction counters.mockup-codefor viewing synthesized Markdown memory constructs with token downsampling ratios.
🕹️ Ghost Cursor Telemetry Engine
- Organic Bézier Trajectories: Natural cubic Bézier curve calculation with quintic ease-in/ease-out acceleration, micro-jitter, and target deceleration.
- Focus-Independent CDP Delivery: Input events are dispatched over the tab's already-attached Chrome DevTools Protocol debugger (
Input.dispatchMouseEvent/Input.dispatchKeyEvent/Input.mouseWheel), withEmulation.setFocusEmulationEnabledso focus-gated page JS still responds. Clicks, keystrokes, and momentum wheel scrolling land regardless of which window owns the OS foreground.webContents.sendInputEventremains only as a fallback (and only that path needs the window focused). The active transport is reported bybridge_health→input.transport(cdp|native). - Anti-Bot Defense Bypass: Avoids heuristic bot triggers by behaving like an authentic human operator; every interaction is
isTrusted: truebecause it is genuine browser input, not a synthetic DOM.click().
🎛️ Focus-Independent Input & Background Rendering
Two real-desktop failure modes are handled explicitly so long harvests and HIL flows stay reliable:
- Input is not tied to OS focus. Synthetic input is delivered over CDP and therefore reaches the renderer even while you work in another application. If the debugger is unavailable the simulator falls back to
webContents.sendInputEventand brings the window forward first (that path is the only one that steals the foreground).bridge_healthexposesinput.transportso an agent can tell which path is live. - Occluded windows keep rendering. Browsing tabs run with
backgroundThrottling: false, and the app boots with--disable-backgrounding-occluded-windows,--disable-renderer-backgrounding, and--disable-background-timer-throttling. Without these, Chromium reports the pagehidden, throttles timers to ≥1s, and stops producing frames — soscrollevents never fire andIntersectionObserver/rAF hydration stalls (the classic "lazy list stops growing" bug). - Viewport gating is explicit. Real input needs a non-zero viewport; a fresh or hidden tab can briefly report
0x0. Callset_window_visibility({ visible: true })and wait for a non-zero viewport before acting. Showing the window is otherwise only needed to make it visible to a human (HIL).
Hypagon Gateway MCP questions
What tools does Hypagon Gateway MCP provide?
It exposes 17 tools, including navigate, observe, find, act, wait_for.
What is Hypagon Gateway?
It is a visible, stateful web browser that any MCP agent can drive, providing a real Chromium window on your machine controlled over the Model Context Protocol.
Which AI assistants can use this tool?
Any assistant that supports the Model Context Protocol (MCP), including Claude Desktop and Cursor, can drive it.
Is this a headless browser?
No, it is a visible Chromium browser with hardware acceleration, real tabs, and a human-sized viewport.