Expose AnyWidget interfaces through MCP Apps and WebMCP
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"anywidget-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<p align="center"> <a href="https://peter-gy.github.io/anywidget-mcp/"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://peter-gy.github.io/anywidget-mcp/brand/anywidget-mcp-logo-horizontal-inverse.svg"> <img alt="anywidget-mcp" src="https://peter-gy.github.io/anywidget-mcp/brand/anywidget-mcp-logo-horizontal.svg" width="620"> </picture> </a> </p> <p align="center"> <a href="https://pypi.org/project/anywidget-mcp/"><img alt="PyPI" src="https://img.shields.io/pypi/v/anywidget-mcp.svg"></a> <a href="https://spdx.org/licenses/MIT.html"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-blue.svg"></a> </p> `anywidget-mcp` runs [AnyWidgets](https://anywidget.dev/) inside AI conversations. Interact with a Python widget, then let the model respond to its current state. Connect through a host that supports [MCP Apps](https://modelcontextprotocol.io/extensions/apps/overview), the Model Context Protocol extension for interactive interfaces. It also exposes widgets already running in a notebook as [WebMCP](https://webmachinelearning.github.io/webmcp/) tools for browser agents, including notebooks running Python in WebAssembly. <p align="center"> <img alt="Choose a color, then explore an interactive HEX-to-RGB explanation" src="https://peter-gy.github.io/anywidget-mcp/demos/anywidget-mcp-demo-00.gif" width="900"> </p> - **Bring existing widgets.** Serve widgets from a package or reuse the ones you develop in Jupyter and marimo. - **Accept conversational input.** Typed Python factories become tools that create a fresh widget for each call. - **Share selected state.** Python validates interactions, and you choose which values the model can read. - **Explore large datasets.** Serve [query-backed viewers](https://peter-gy.github.io/anywidget-mcp/large-widgets) such as Embedding Atlas and share their current filter with the model. - **Compose interfaces.** Expose several tools, return a group of wid…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.