Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@review-md review the file ./docs/api-guide.md and send me the annotations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Review Markdown files in your browser with inline annotations. Submit or cancel the review, and get structured feedback back on the command line or through MCP.
npm install -g alson-annotation
review-md document.mdThe review opens in your browser. Select text, add annotations and comments, then send the feedback. The CLI prints the feedback as JSON.
Related MCP server: GitHub Style Markdown Preview MCP App
Node.js 18 or newer
Method | Command |
Global (recommended) |
|
Run once without install |
|
From GitHub |
|
From source |
|
review-md <file> [options]Argument / option | Description |
| Path to the Markdown file to review (required) |
| Path to a questions JSON file |
| Preferred port for the local server |
| Print help |
| Print version |
The review can include questions for the reviewer. Pass a JSON file with --questions.
[
{
"id": "overall-quality",
"type": "single-select",
"label": "Overall quality",
"options": [
{ "id": "good", "label": "Good" },
{ "id": "needs-work", "label": "Needs work" }
],
"required": true
}
]type: single-select or multi-select
required: optional, defaults to false
IDs must match ^[a-zA-Z0-9_-]+$
On submit, the CLI prints structured feedback as JSON:
{
"action": "submitted",
"file_path": "/path/to/document.md",
"annotations": [
{
"id": "ann-001",
"source_location": { "start_line": 1, "start_col": 1, "end_line": 1, "end_col": 10 },
"selected_text": "Hello",
"comment": "Great intro"
}
],
"document_comments": ["Nice document"],
"questions": { "overall-quality": "good" }
}If the reviewer cancels, the output is { "action": "cancelled", "file_path": "..." }.
The package includes an MCP server that exposes a review_markdown tool. Configure it in any MCP client:
{
"mcpServers": {
"review-md": {
"command": "review-md-mcp"
}
}
}The tool takes file_path (required) and optional inline questions. The review blocks until the reviewer submits or cancels, then returns the structured feedback.
npm uninstall -g alson-annotationnpm ci
npm run build
npm testnpm run build compiles the CLI and MCP server with tsc and the web app with Vite.
npm test runs the vitest suite (unit, CLI, and MCP integration tests).
The dist/ folder is committed so the package works when installed directly from GitHub.
MIT
This server cannot be deployed
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
MarkupBase turns AI-generated Markdown and HTML into durable, versioned artifacts that people can review and discuss. Its MCP server lets agents publish new versions, preserve contextual comments, include hosted images, and respond to feedback through secure account-linked identities, creating a clear human review boundary without requiring real-time editing.
MCP-native collaborative markdown editor with real-time AI document editing
Create, edit, review, and explicitly publish Live or Snapshot Markdown Documents in mdedit.ai.
