# webmachinelearning/webmcp

🤖 WebMCP

Repository: https://github.com/webmachinelearning/webmcp
Canonical: https://ross.abutalabs.com/products/webmcp
Homepage: https://webmachinelearning.github.io/webmcp/
Language: Bikeshed
License: NOASSERTION
License Family: other
Last push: 2026-08-26T20:23:24+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 28
- inputs: {"age_days": 393, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3290, forks 214 (observed 2026-08-28T04:07:50.515871+00:00)

## What it is
WebMCP is a proposed web platform API (W3C Community Group specification) that lets web developers expose JavaScript functions or HTML forms as structured 'tools' with natural language descriptions for AI agents to invoke. It acts like a Model Context Protocol server implemented in client-side browser script, enabling agents to actuate web applications while preserving shared UI context.

## Use cases
- expose web app functionality as tools for AI agents
- let browser AI assistants interact with my web page
- make my website controllable by LLM agents
- build client-side MCP tools without a backend server
- enable AI agents to fill forms and actuate web UI
- share user session context with in-browser agents

## When to choose
- you want AI agents to interact with your web app's client-side logic and UI
- you want to avoid building backend tool integrations and replicating auth/state server-side
- you want cooperative user-agent workflows within your existing web interface

## When to avoid
- you need server-to-server tool integrations with AI platforms like ChatGPT or Claude
- you need a stable, widely-supported standard today - browser support is still limited
- your app has no meaningful client-side functionality to expose

## Facets
- artifact type: library
- maturity: experimental
- function: mcp, agent-framework, sdk, api-framework
- domain: artificial-intelligence, web-development, browser-extensions, large-language-models
- platform: browser, browser-extension
- tags: web-standards, client-side-tools, w3c-specification, ai-agents, model-context-protocol, browser-api, web-server, javascript

## Member repositories
- webmachinelearning/webmcp (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:50.515871+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:22:50.026167+00:00, confidence not recorded.
  - readme: https://github.com/webmachinelearning/webmcp (fetched 2026-08-28T04:07:50.515871+00:00, sha 95a9516e9ca8)
  - homepage: https://webmachinelearning.github.io/webmcp/ (fetched 2026-08-29T09:35:45.210357+00:00, sha 823d9fbbbb13)
- Data as of 2026-08-30T08:39:29.467469+00:00.