What are the peer dependencies?
You need `@codemirror/view`, `@codemirror/state`, and `@modelcontextprotocol/sdk`.
@marimo-team
基本情報
CodeMirror extension to hook up a Model Context Provider (MCP)
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A CodeMirror extension that implements the Model Context Protocol (MCP) for autocompleting @resource mentions and /prompt commands, with visual decorations and click handling. It's designed for developers building AI-assisted editors or chat interfaces on top of CodeMirror.
Install with npm install @marimo-team/codemirror-mcp @modelcontextprotocol/sdk and peer dependencies. Import mcpExtension and pass it to an EditorView with a transport (e.g., WebSocketClientTransport) and optional options like logger, clientOptions, and onResourceClick. Use extractResources(view) to collect referenced resources for submission.
@resource mentions/prompt commandsextractResourcesYou need `@codemirror/view`, `@codemirror/state`, and `@modelcontextprotocol/sdk`.
The extension accepts any MCP transport; the README shows `WebSocketClientTransport` connecting to `ws://localhost:8080`.
Yes, the extension supports customizable styling via theme options.
Use the `extractResources(view)` function to get an array of resources from the editor state.
Resources and prompts are handled client-side; network transport depends on the provided MCP transport (e.g., WebSocket).
Hindsight: Agent Memory That Learns

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Open-source MCP to use Blender with any LLM
A search tool helps dev to solve the naming things problem.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
コメント