Qiita MCP Server
About
It is a Model Context Protocol (MCP) server that enables AI agents to interact with Qiita, the knowledge-sharing platform for engineers. It provides standardized tools for creating, reading, and updating Qiita articles.
Details
- Author
- 2bo
- Downloads
- 239
- Categories
- Other, API
Jump to
- Get current authenticated user’s Qiita articles
- Retrieve a specific Qiita article by its ID
- Create a new article on Qiita
- Update an existing Qiita article
- Obtain Qiita markdown syntax rules and cheat sheet
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Qiita MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via npx with Node.js 20+ and a Qiita API token. Configure the server in your VS Code project by adding an entry to .vscode/mcp.json using the command npx @2bo/qiita-mcp-server and setting the QIITA_API_TOKEN environment variable.
get_my_qiita_articles
get current authenticated user qiita articles
get_qiita_item
get a specific Qiita article by its ID
update_qiita_article
update an existing Qiita article
post_qiita_article
create a new article on Qiita
get_qiita_markdown_rules
get Qiita markdown syntax rules, cheat sheet
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"qiita mcp server": {
"qiita-mcp-server": {
"command": "npx",
"args": [
"@2bo/qiita-mcp-server"
],
"env": {
"QIITA_API_TOKEN": ""
}
}
}
}
}McpServers
{
"qiita-mcp-server": {
"command": "npx",
"args": [
"@2bo/qiita-mcp-server"
],
"env": {
"QIITA_API_TOKEN": ""
}
}
}Qiita MCP Server
A Model Context Protocol (MCP) server for interacting with Qiita, the knowledge-sharing platform for engineers.
Overview
This package provides a Model Context Protocol (MCP) server that enables AI agents to interact with the Qiita API. It allows for creating, reading, and updating articles on Qiita through standardized MCP tools.
MCP is an open protocol for building AI agents that can use external tools and services. This server implements the MCP specification to provide tools for working with Qiita content.
Provided Tools
The server provides the following MCP tools:
| Tool Name | Description |
|-----------|-------------|
| get_my_qiita_articles | Get current authenticated user's Qiita articles |
| get_qiita_item | Get a specific Qiita article by its ID |
| post_qiita_article | Create a new article on Qiita |
| update_qiita_article | Update an existing Qiita article |
| get_qiita_markdown_rules | Get Qiita markdown syntax rules and cheat sheet |
Usage
Prerequisites
- Node.js (>=20.0.0)
- A Qiita account with API access token
- You can generate a Qiita API token by visiting: https://qiita.com/settings/tokens/new
Usage with VS Code
1. Create a .vscode/mcp.json file in your project with the following content:
{
"inputs": [
{
"type": "promptString",
"id": "qiita-api-token",
"description": "Qiita API Token",
"password": true
}
],
"servers": {
"qiita-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["@2bo/qiita-mcp-server"],
"env": {
"QIITA_API_TOKEN": "${input:qiita-api-token}"
}
}
}
}
Development
Setup
1. Clone the repository:
git clone https://github.com/2bo/qiita-mcp-server.git
cd qiita-mcp-server
2. Install dependencies:
npm install
3. Set up your environment:
- npm run dev - Run TypeScript in watch mode for development
- npm run build - Build the project
- npm run prepare - Prepare the package for publishing
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
