review-md
Enables reviewing Markdown files in a browser with inline annotations, submitting or cancelling reviews, and returning structured feedback through the review_markdown MCP tool.
README
alson-annotation
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.
Quick start
npm install -g alson-annotation
review-md document.md
The review opens in your browser. Select text, add annotations and comments, then send the feedback. The CLI prints the feedback as JSON.
Requirements
- Node.js 18 or newer
Install
| Method | Command |
|---|---|
| Global (recommended) | npm install -g alson-annotation |
| Run once without install | npx alson-annotation document.md |
| From GitHub | npm install -g github:agnojf/alson-annotation |
| From source | git clone https://github.com/agnojf/alson-annotation.git then npm ci && npm run build |
Usage
review-md <file> [options]
| Argument / option | Description |
|---|---|
<file> |
Path to the Markdown file to review (required) |
--questions, -q <path> |
Path to a questions JSON file |
--port, -p <number> |
Preferred port for the local server |
--help, -h |
Print help |
--version, -v |
Print version |
Questions file
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-selectormulti-selectrequired: optional, defaults tofalse- IDs must match
^[a-zA-Z0-9_-]+$
Output
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": "..." }.
MCP server
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.
Uninstall
npm uninstall -g alson-annotation
Development
npm ci
npm run build
npm test
npm run buildcompiles the CLI and MCP server withtscand the web app with Vite.npm testruns the vitest suite (unit, CLI, and MCP integration tests).- The
dist/folder is committed so the package works when installed directly from GitHub.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.