{"slug": "web-mcp-bridge-connect-browser-based-llms-to-mcp-servers-and-tools", "title": "Web-MCP-Bridge – Connect browser-based LLMs to MCP servers and tools", "summary": "A new open-source browser extension called Web MCP Bridge lets ChatGPT, Gemini and Claude web interfaces call local Model Context Protocol (MCP) servers without API keys or paid subscriptions, routing tool requests through a Python bridge that listens on 127.0.0.1 and accepts only chrome-extension:// origins. The project ships adapters for all three platforms (adapters/chatgpt.js, adapters/gemini.js, adapters/claude.js), requires per-call approval by default, and claims roughly 50% fewer tokens by describing tools as name(param: type) signatures instead of JSON Schema. A new platform integration takes about 40 lines of selectors, and the repo includes a demo MCP server for a 60-second quick start.", "body_md": "**Use your local MCP servers with ChatGPT, Gemini and Claude Web: no API keys, no extra subscriptions.**\n\nFree AI chat UIs don't speak MCP. **Web MCP Bridge** adds it: the model asks for a tool with a JSON block,\nthe extension runs it on your local MCP server over WebSocket and pastes the result back into the chat.\nBy default you approve every call.\n\nImportant\n\nOnly connect MCP servers you trust. A tool with filesystem access can read whatever you allow it to.\n\n| Platform | Status | Adapter | \n|---|---|---|\n|  | ✅ Supported | `adapters/chatgpt.js` | \n|  | ✅ Supported | `adapters/gemini.js` | \n|  | ✅ Supported | `adapters/claude.js` | \n|  [·](https://camo.githubusercontent.com/d07fc3deb7c4cfed1fddd8ca223a4c9c3153dcb12bb48c267834e87c6437f144/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f506572706c65786974792d3146423843443f7374796c653d666f722d7468652d6261646765266c6f676f3d706572706c6578697479266c6f676f436f6c6f723d7768697465)  [·](https://camo.githubusercontent.com/cfeeb479b240f7f30d30d834e294edd48b1a6c4a9fef7a2f2cc123965d939372/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f446565705365656b2d3444364246453f7374796c653d666f722d7468652d6261646765)  | 🗺️ Roadmap | [Contribute](https://github.com/AstraxOf/web-mcp-bridge/blob/main/CONTRIBUTING.md) | \n\n|  | Skill | What it does | \n|---|---|---|\n|  | **Context control** | Register many servers, **1 active by default** (up to**5** ). Only active servers' tools reach the model; the popup shows the approximate token cost. | \n|  | **Per-MCP permissions** | 3-state selector — *Allow always* ·*Ask every time* ·*Don't allow* — global and per server, in the popup and the in-page panel. | \n|  | **Nothing is dropped** | Images, audio and binary resources are attached to the chat as real files; long text is attached in full instead of truncated. | \n|  | **No preinstalled MCP** | Add your own, or the bundled demo server with one click. | \n|  | **Reliable in the background** | No step relies on page timers (throttled when hidden); delivery is verified and retried. | \n|  | **The AI doesn't forget** | A one-line reminder per message plus periodic full re-injection. | \n|  | **≈ 50 % fewer tokens** | Tools are described as `name(param: type)` signatures instead of JSON Schema. | \n|  | **~40 lines per platform** | A new platform is just a set of selectors. | \n|  | **Locked down** | The Python bridge listens on `127.0.0.1` , only accepts`chrome-extension://` origins and supports a token. Websites can't reach your tools. | \n|  | **No duplicates, auto-reconnect** | Per-call IDs, exponential backoff, keep-alive for the MV3 Service Worker, call history, light/dark UI. | \n\nTip\n\nWant to try it in 60 seconds? The repo ships with a **demo MCP server**. See [Quick start](#-quick-start-60-seconds).\n\nBrowsers can't launch local programs, so run this **once**. It keeps the bridge running in the background at login (Windows / macOS / Linux):\n\n```\npython server/install_service.py\n```\n\nThen load the extension. Use the **master switch in the popup** (or the in-page panel) to turn the bridge on/off; the icon shows `OFF` when disabled.\nRemove auto-start with `python server/install_service.py --uninstall`.\n\n```\npip install -r server/requirements.txt\npython server/mcp_ws_bridge.py --port 8080 --name demo -- python server/examples/demo_mcp_server.py\n```\n\n1. `chrome://extensions` → enable**Developer mode** →**Load unpacked** → select this folder.\n2. Open the popup and add your server (e.g. `astrax_mcp` at`ws://localhost:8080` ), or click**Add demo server** .\n3. Open ChatGPT / Gemini / Claude → open the **Web MCP Bridge** panel (bottom-left) →**Inject instructions** .\n4. Ask *\"What time is it? Use your tools.\"* and approve the call.\n\n**Your own server:**\n\n```\npython server/mcp_ws_bridge.py --port 8080 -- python -m astrax_mcp\n```\n\n**Several at once:** see `server/servers.example.json` and `--config`.\n\n```\n{ \"mcp_call\": { \"server\": \"server_name\", \"name\": \"tool_name\", \"arguments\": { \"arg1\": \"value\" } } }\n```\n\nResults come back as:\n\n```\n[MCP_RESULT server=\"…\" tool=\"…\" status=\"ok|error|rejected\"]\n…\n[/MCP_RESULT]\n```\n\nNote\n\nThe content of `MCP_RESULT` is presented to the AI as *data*, not instructions (prompt-injection mitigation).\n\nSee the [Spanish README](https://github.com/AstraxOf/web-mcp-bridge/blob/main/README.es.md) for the architecture diagram, security model, selector-fix guide and roadmap.\n\n```\nnpm test      # syntax, parser, prompt builder and bridge integration tests\nnpm run pack  # dist/web-mcp-bridge.zip\n```\n\n**Astrax** is open source and grows with its community. You're welcome to open issues, send pull requests, suggest ideas, try Astrax on other systems or MCP clients, and report bugs. Read [CONTRIBUTING.md](https://github.com/AstraxOf/web-mcp-bridge/blob/main/CONTRIBUTING.md) to get started — new adapters are the best first contribution.\n\nIf you find the project useful, leave a ⭐ on the repository and subscribe to the channel.\n\nMade with 💙 by Rufus · [@AstraxOf](https://github.com/AstraxOf) · [astrabots.pro](https://astrabots.pro)", "url": "https://wpnews.pro/news/web-mcp-bridge-connect-browser-based-llms-to-mcp-servers-and-tools", "canonical_source": "https://github.com/AstraxOf/web-mcp-bridge", "published_at": "2026-10-30 21:27:04+00:00", "updated_at": "2026-10-30 21:46:47.981641+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "developer-tools", "large-language-models"], "entities": ["Web MCP Bridge", "Model Context Protocol", "ChatGPT", "Gemini", "Claude", "AstraxOf"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/web-mcp-bridge-connect-browser-based-llms-to-mcp-servers-and-tools", "markdown": "https://wpnews.pro/news/web-mcp-bridge-connect-browser-based-llms-to-mcp-servers-and-tools.md", "text": "https://wpnews.pro/news/web-mcp-bridge-connect-browser-based-llms-to-mcp-servers-and-tools.txt", "jsonld": "https://wpnews.pro/news/web-mcp-bridge-connect-browser-based-llms-to-mcp-servers-and-tools.jsonld"}}