go-mcp-server-mds
@Warashi
About go-mcp-server-mds
A Go implementation of a Model Context Protocol (MCP) server that serves markdown files with frontmatter support from a filesystem.
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is go-mcp-server-mds?
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.
How to use go-mcp-server-mds?
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.
Key features of go-mcp-server-mds
- Serves markdown files over MCP as resources and tools
- Lists all markdown files with metadata and frontmatter
- Reads individual markdown file content and frontmatter
- Supports YAML (
---) and TOML (+++) frontmatter - Uses Go’s
fs.FSfor filesystem abstraction - URI-based resource access via
file://URIs
Use cases of go-mcp-server-mds
- Making a local documentation folder accessible to an MCP-powered AI assistant
- Exposing markdown notes with structured frontmatter for search or organization
- Building an MCP-based tool that needs to read and serve markdown files from any directory
- Integrating markdown content into larger MCP workflows (e.g., summarization or retrieval)
FAQ from go-mcp-server-mds
What frontmatter formats are supported?
YAML frontmatter (delimited by ---) and TOML frontmatter (delimited by +++) are both fully supported.
How are resources accessed?
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.
How can I customize the server name or description?
Use the -name and -description flags when running the CLI tool, or pass them as string arguments to the mcpmds.New function.
What transport does the server use?
The server uses standard input/output (stdio) via the ServeStdio method.
Are there any runtime dependencies?
Only Go itself; the server is a self-contained Go binary that reads markdown files from the local filesystem specified by the -path flag.
More Files & Storage MCP servers
Storacha MCP Storage Server
storachaStoracha MCP storage server - self-sovereign data for your AI applications.
S3 MCP Server
samuraikunMCP server to integrate AWS S3 and LLM
mcp-v8: V8 JavaScript MCP Server
r33drichardsMCP 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 File System Server
MarcusJellinghausMCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
mcp-rquest
xxxbrianA MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
Comments