Sandbox
@nickytonline/dev-to-mcp

MCP server for dev.to API access

This project wraps the dev.to public API in a remote MCP server so compatible agents can query dev.to content directly. It exposes tools for articles, users, tags, comments, and search, and runs over HTTP on port 3000 or `/mcp` in Docker.

45 stars17 forksTypeScriptUpdated 11mo ago
Who it's for

Builders who want their agent to pull dev.to articles and metadata through MCP.

What it delivers

You can ask an MCP client to fetch dev.to content without setting up dev.to authentication yourself.

What it does

Article access

Provides `get_articles` and `get_article` for listing articles or opening one by ID or path.

User and tag lookup

Provides `get_user` and `get_tags` for author details and popular tags.

Comment retrieval

Provides `get_comments` for comments on a specific article.

Article search

Provides `search_articles` with query, paging, and field filters.

Remote MCP transport

Runs as an HTTP server so any MCP-compatible client can connect to it.

How to get it

  1. 1If you want to install and build from source using npm
    npm install
    npm run build
  2. 2The server runs as a remote HTTP server on port 3000 (or the PORT environment variable)…
    npm start

README

Dev.to MCP Server

A remote Model Context Protocol (MCP) server for interacting with the dev.to public API without requiring authentication.

Features

This MCP server provides access to the following dev.to public API endpoints:

  • get_articles - Get articles from dev.to with optional filters (username, tag, state, pagination)
  • get_article - Get a specific article by ID or path
  • get_user - Get user information by ID or username
  • get_tags - Get popular tags from dev.to
  • get_comments - Get comments for a specific article
  • search_articles - Search articles using query parameters

Installation

Using npm

If you want to install and build from source using npm:

npm install
npm run build

Usage

The server runs as a remote HTTP server on port 3000 (or the PORT environment variable) and can be used with any MCP-compatible client.

npm start

The server will be available at http://localhost:3000 for MCP connections.

Development

# Build the project
npm run build

# Watch mode for development
npm run dev

# Linting
npm run lint
npm run lint:fix

# Formatting
npm run format
npm run format:check

Docker

Using Pre-built Image

Pull and run the pre-built Docker image:

# Pull the image
docker pull docker.io/nickytonline/dev-to-mcp:latest

# Run it
docker run -d \
  --name dev-to-mcp \
  -e NODE_ENV=production \
  -e PORT=3000 \
  -p 3000:3000 \
  --restart unless-stopped \
  docker.io/nickytonline/dev-to-mcp:latest

Once it's up, check health status via:

curl -fsS http://127.0.0.1:3000/mcp

The server will be available at http://localhost:3000/mcp for MCP connections.

Building from Source

Build and run the MCP server using Docker:

# Build the Docker image
docker build -t dev-to-mcp .

# Run the container
docker run -p 3000:3000 dev-to-mcp

Docker Compose

Using the pre-built image with Docker Compose:

services:
  dev-to-mcp:
    image: docker.io/nickytonline/dev-to-mcp:latest
    container_name: dev-to-mcp
    restart: unless-stopped
    environment:
      NODE_ENV: production
      PORT: 3000
    networks:
      - main
    healthcheck:
      # Uses $PORT at runtime; defaults to 3000 if not set
      test:
        [
          "CMD-SHELL",
          "curl -fsS http://127.0.0.1:${PORT:-3000}/mcp >/dev/null || exit 1",
        ]
      interval: 15s
      timeout: 5s
      retries: 5
      start_period: 30s

networks:
  main: {}

For development with a local build, you can also use Docker Compose:

# docker-compose.yml
version: "3.8"
services:
  dev-to-mcp:
    build: .
    ports:
      - "3000:3000"
    environment:
      - PORT=3000
docker-compose up --build

API Endpoints

All endpoints use the public dev.to API (https://dev.to/api) and do not require authentication.

get_articles

Get articles with optional filtering:

  • username - Filter by author username
  • tag - Filter by tag
  • top - Top articles (1, 7, 30, or infinity days)
  • page - Pagination page (default: 1)
  • per_page - Articles per page (default: 30, max: 1000)
  • state - Filter by state (fresh, rising, all)

get_article

Get a specific article:

  • id - Article ID
  • path - Article path (e.g., "username/article-slug")

get_user

Get user information:

  • id - User ID
  • username - Username

get_tags

Get popular tags:

  • page - Pagination page (default: 1)
  • per_page - Tags per page (default: 10, max: 1000)

get_comments

Get comments for an article:

  • article_id - Article ID (required)

search_articles

Search articles:

  • q - Search query (required)
  • page - Pagination page (default: 1)
  • per_page - Articles per page (default: 30, max: 1000)
  • search_fields - Fields to search (title, body_text, tag_list)

License

MIT

Files in the repo

Repository payload17 top-level entries
  • .github
  • src
  • .copilot-instructions.md
  • .cursorrules
  • .dockerignore
  • .gitignore
  • .prettierrc
  • CLAUDE.md
  • CODE-OF-CONDUCT.md
  • CONTRIBUTING.md
  • Dockerfile
  • eslint.config.js
  • package-lock.json
  • package.json
  • README.md
  • tsconfig.json
  • vite.config.ts

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

1.9k