jasonjmcghee/WebMCP

Early WebMCP proposal / implementation - since evolved and worked on by much more capable folks that develop the web: https://github.com/webmachinelearning/webmcp

51
/ 100
Established

This project helps website owners integrate client-side Large Language Models (LLMs) directly into their sites. It provides a widget that allows websites to act as an "MCP server," exposing tools, resources, and prompts to a user's local LLM. The end result is a website that can interact with a user's AI assistant, letting the AI use website-specific functionalities.

579 stars.

Use this if you are a website owner or web developer who wants to enable client-side AI assistants to interact with your website's features and content directly, without sharing API keys.

Not ideal if you are looking for the official, W3C-compliant Web Machine Learning Command Protocol (WebMCP) specification or implementation, as this is an early, non-compliant proposal.

web-development AI-integration user-experience client-side-LLMs website-interactivity
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

579

Forks

45

Language

JavaScript

License

MIT

Last pushed

Feb 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/jasonjmcghee/WebMCP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.