Dev.to MCP Server
开发人员到 MCP 服务器
该存储库包含 Dev.to 的模型上下文协议服务器实现,允许 AI 助手访问并与 Dev.to 内容交互。

什么是 MCP?
模型上下文协议 (MCP) 是一项标准,用于支持 AI 助手与外部服务、工具和数据源进行交互。此服务器实现了 MCP 规范,以提供对 Dev.to 内容的访问。要了解更多关于 MCP 的信息,请观看此视频
Related MCP server: devto-mvp-server
特征
从 Dev.to 获取最新和热门文章
按不同标准搜索文章
获取特定文章的详细信息
获取有关用户的详细信息。
通过标签或用户名访问文章
创建并发布新文章到 Dev.to
更新现有文章
缓存机制以提高性能并减少 API 调用
安装
克隆此存储库
git clone https://github.com/Arindam200/devto-mcp.git
cd devto-mcp连接到 MCP 服务器
使用适当的 {{PATH}} 值复制以下 json:
{ "mcpServers": { "devto": { "command": "{{PATH_TO_UV}}", // Run `which uv` and place the output here "args": [ "--directory", "{{PATH_TO_SRC}}",// cd into the repo, run `pwd` and enter the output here "run", "server.py" ], "env": { "DEV_TO_API_KEY":"Your Dev.to API Key" // Get it from https://dev.to/settings/extensions. } } } }您可以从Dev.to 设置页面获取 Dev.to API 密钥。
对于Claude ,将其保存为
claude_desktop_config.json并保存在 Claude Desktop 配置目录中:~/Library/Application Support/Claude/claude_desktop_config.json对于Cursor ,将其保存为
mcp.json并保存在 Cursor 配置目录中:~/.cursor/mcp.json重启 Claude Desktop/Cursor
打开 Claude Desktop,您现在应该看到 Devto 是一个可用的集成。
或者重新启动 Cursor。
可用工具
该服务器提供以下工具:
get_latest_articles()- 从 Dev.to 获取最新文章get_top_articles()- 从 Dev.to 获取最受欢迎的文章get_articles_by_tag(tag)- 通过标签获取文章get_article_by_id(id)- 通过 ID 获取特定文章search_articles(query, page=1)- 通过标题/描述中的关键词搜索文章get_article_details(article_id)- 获取特定文章的完整内容和元数据get_articles_by_username(username)- 获取特定作者撰写的文章create_article(title, body_markdown, tags, published)- 创建并发布新文章update_article(article_id, title, body_markdown, tags, published)- 更新现有文章
示例查询
以下是您可以向连接到该服务器的 AI 助手询问的一些示例:
“在 Dev.to 上查找有关 Python 的文章”
“向我展示最新的 Dev.to 文章”
“获取文章 1234 的详细信息”
“用户‘ben’写了哪些文章?”
“搜索有关机器学习的文章”
“创建一篇题为‘Python 入门’的新文章”
“更新我的 ID 为 5678 的文章,以修复内容中的拼写错误”
高级功能
自定义提示
服务器提供了可供AI助手使用的预定义提示:
search_prompt- 创建格式化的搜索提示analyze_article- 创建提示来分析特定文章
验证
服务器需要 Dev.to API 密钥才能执行某些操作,尤其是创建和更新文章。API 密钥应设置为环境变量DEV_TO_API_KEY 。
贡献
欢迎贡献代码!欢迎提交 Pull 请求。
执照
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅 LICENSE 文件。
Available Tools
10 toolscreate_articleB
Create and publish a new article on Dev.to
Args:
title: The title of the article
body_markdown: The content of the article in markdown format
tags: Comma-separated list of tags (e.g., "python,tutorial,webdev")
published: Whether to publish immediately (True) or save as draft (False)
Inputs: title (required), body_markdown (required), tags, published.
get_article_by_idC
Get a specific article by ID from Dev.to
Inputs: id (required).
get_article_detailsC
Get detailed information about a specific article
Args:
article_id: The ID of the article to retrieve
Inputs: article_id (required).
get_articles_by_tagC
Get articles by tag from Dev.to
Inputs: tag (required).
get_articles_by_usernameC
Get articles written by a specific user
Args:
username: The username of the author
Inputs: username (required).
get_latest_articlesB
Get the latest articles from Dev.to
Inputs: no named parameters.
get_top_articlesB
Get the top articles from Dev.to
Inputs: no named parameters.
get_user_infoC
Get information about a Dev.to user
Args:
username: The username of the user
Inputs: username (required).
search_articlesB
Search for articles on Dev.to
Args:
query: Search term to find articles
page: Page number for pagination (default: 1)
Inputs: query (required), page.
update_articleB
Update an existing article on Dev.to
Args:
article_id: The ID of the article to update
title: New title for the article (optional)
body_markdown: New content in markdown format (optional)
tags: New comma-separated list of tags (optional)
published: Change publish status (optional)
Inputs: article_id (required), title, body_markdown, tags, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have distinct purposes targeting different operations (create, get, update, search), but there is some ambiguity between get_article_by_id and get_article_details which appear to serve similar retrieval functions. The other tools are clearly differentiated by their target data or action.
All tools follow a consistent verb_noun pattern with snake_case throughout (e.g., create_article, get_articles_by_tag, update_article). The naming is predictable and follows a clear convention without any deviations in style or structure.
With 10 tools, this server is well-scoped for managing Dev.to content, covering core operations like CRUD for articles, user info retrieval, and various query methods. Each tool serves a specific purpose without bloat, making the count appropriate for the domain.
The toolset provides comprehensive coverage for article management (create, read, update, search) and user information, but lacks delete functionality for articles, which is a minor gap. Core workflows are supported, and agents can likely work around the missing delete operation.
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Hosted MCP server for live public-data APIs and Skills for AI agents.
Web search API and MCP server for developers building AI agents.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that enables AI assistants like Claude to interact with Substack newsletters, allowing for post retrieval, content searching, and author information access through a standardized interface.MIT
- AlicenseNot gradedqualityDmaintenanceThis is a complete MCP (Model Context Protocol) server that implements a articles of dev.to with robust validation using TypeScript and Zod. The server integrates directly with Cursor, allowing you search articles on dev.to.MIT
- AlicenseAqualityDmaintenanceA production-ready MCP server for the DEV Community (Forem) API, enabling management of articles, comments, users, tags, organizations, reading list, and followers through any MCP-compatible client.167 npm6MIT
- FlicenseNot gradedqualityDmaintenanceProvides MCP tools to interact with Dev.to, enabling searching, browsing, and publishing articles through natural language.-