Zenn MCP Server
# mcp-server-zenn: Unofficial MCP server for Zenn (https://zenn.dev/)
## Overview
This is an unofficial Model Context Protocol server for [Zenn](https://zenn.dev/). Build on top of [Zenn's dev API](https://zenn.dev/api/).
## Features
- Fetch a list of articles
- Fetch a list of books
## Run this project locally
This project is not yet set up for ephemeral environments (e.g. `uvx` usage). Run this project locally by cloning this repo:
```shell
git clone https://github.com/shibuiwilliam/mcp-server-zenn.git
```
You can launch the [MCP inspector](https://github.com/modelcontextprotocol/inspector) via [npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm):
```shell
npx @modelcontextprotocol/inspector uv --directory=src/mcp_server_zenn run mcp-server-zenn
```
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
OR
Add this tool as a MCP server:
```json
{
"zenn": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-server-zenn",
"run",
"mcp-server-zenn"
]
}
}
```
## Deployment
(TODO)
## [License](./LICENSE)
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one fetches articles and the other fetches books from Zenn.dev. There is no overlap in functionality, and an agent can easily differentiate between them based on the resource type (articles vs. books).
Both tools follow a consistent naming pattern using simple, descriptive nouns (article and book) that directly indicate the resource being fetched. There are no deviations in style or convention, making the naming straightforward and predictable.
With only two tools, the server feels thin for a content platform like Zenn.dev. While fetching articles and books covers core read operations, the lack of tools for creating, updating, or managing content (e.g., publishing, searching, or user interactions) makes the set under-scoped for typical agent workflows.
The tool set is severely incomplete for a Zenn.dev server. It only supports fetching articles and books, missing essential operations such as creating or updating content, searching, managing user profiles, or handling interactions (e.g., likes, comments). This will likely cause agent failures when trying to perform common tasks beyond basic retrieval.