What frontmatter formats are supported?
YAML frontmatter (delimited by `---`) and TOML frontmatter (delimited by `+++`) are both fully supported.
@Warashi
基本情報
A Go implementation of a Model Context Protocol (MCP) server that serves markdown files with frontmatter support from a filesystem.
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 Go implementation of a Model Context Protocol (MCP) server that serves markdown files from a filesystem. It exposes markdown files as resources with URI-based access and provides tools to list and read them, supporting YAML and TOML frontmatter. Targeted at developers who want to make markdown documentation or notes available to MCP clients.
Install with go get github.com/Warashi/go-mcp-server-mds. Use the Go library: create a server with mcpmds.New and start it via server.ServeStdio(context.Background()). Alternatively, install the CLI tool mcp-server-mds with go install github.com/Warashi/go-mcp-server-mds/cmd/mcp-server-mds@latest and run it with -path to specify the markdown directory.
---) and TOML (+++) frontmatterfs.FS for filesystem abstractionfile:// URIsYAML frontmatter (delimited by `---`) and TOML frontmatter (delimited by `+++`) are both fully supported.
Each markdown file is registered as a resource with a `file://` URI (e.g., `file:///path/to/file.md`). The resource includes name, description (JSON-encoded frontmatter), MIME type `text/markdown`, and file size.
Use the `-name` and `-description` flags when running the CLI tool, or pass them as string arguments to the `mcpmds.New` function.
The server uses standard input/output (stdio) via the `ServeStdio` method.
Only Go itself; the server is a self-contained Go binary that reads markdown files from the local filesystem specified by the `-path` flag.
Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.
Go server implementing Model Context Protocol (MCP) for filesystem operations.
MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.

AI tools (Claude, ChatGPT, Gemini, Grok, etc.) generate HTML constantly, from reports to landing pages to prototypes, but there's no easy way to share it or know if anyone looked. HTMLvault turns any HTML into a clean, t
コメント