Urgent.News

What's breaking now, across thousands of outlets.

AI

Turn Free Web AIs (DeepSeek, Gemini, ChatGPT, Claude) into a Local MCP Agent Harness

A raw LLM in a browser tab is just a text predictor—what turns models like DeepSeek, Gemini, ChatGPT, or Claude into real autonomous agents is the agent harness around them. I built Web MCP Bridge to wrap their free web interfaces in a complete local Model Context Protocol (MCP) harness using a Manifest V3 extension and a lightweight Python WebSocket bridge ( 127.0.0.1 ). It lets the web AI read…

DeepSeek, Gemini, ChatGPT, and Claude are large language models (LLMs) that can be transformed into autonomous agents through an agent harness. The web interface of these models can be wrapped in a Model Context Protocol (MCP) harness using a Manifest V3 extension and a lightweight Python WebSocket bridge. This enables the web AI to read files, run terminal commands, and interact with local stdio MCP servers without requiring any API keys, subscriptions, or local GPUs.

In the most recent version, version 1.8.0, the bridge has been optimized to handle hundreds of tools without freezing browser tabs. This is achieved by replacing massive 100k-character schema dumps with a more compact ~2k-character paginated catalog that the models can query on demand. Additionally, a 3-layer self-healing JSON parser has been introduced to fix broken model outputs such as unescaped Windows paths or trailing commas.

The bridge also features a redesigned bilingual UI, supporting both English and Spanish, and dual licensing under MIT and Apache 2.0. All operations are performed locally on the user's machine, with the bridge rejecting non-extension origins, isolating tool outputs to prevent prompt injection, and defaulting to "Ask every time" to ensure no action runs without the user's explicit approval. The bridge's code and quick-start guide are available on GitHub: AstraxOf/web-mcp-bridge.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

No, China's AI bubble did not burst

No, China's AI bubble did not burst newspress_en Tue, 11/17/2026 - 01:27 Business & Economy The fall was as swift as the rise had been noisy.

  • China's AI index declined 40% in 4 months, losing $480B market value
  • Decline doesn't definitively prove AI or chip bubble
  • STAR 50's P/E ratio near 100 despite correction

Llama 4 Scout: What Meta's open-weight multimodal brings to product teams

Originally published on juliancardozo.github.io. Llama 4 Scout is Meta's open-weight multimodal model that is worth looking at when evaluating vision, text, and long context capabilities under a…

  • Llama 4 Scout es modelo multimodal open-weight de Meta.
  • Ofrece visión, texto y contexto largo con 17 mil millones de parámetros activos.
  • Licencia comunitaria impone restricciones para grandes organizaciones.

More from Tuesday 17 November →