Zenn MCP Server

Instructions

Implementation Reference

• src/mcp_server_zenn/server.py:223-226 (handler)

  Handler that processes the arguments for the 'article' tool, parses them into an Article object, and fetches the articles.
  async def handle_articles(arguments: dict) -> dict: query = Article.from_arguments(arguments) return await fetch_articles(query)
• src/mcp_server_zenn/server.py:215-217 (handler)

  Executes the core logic for the 'article' tool by making an HTTP request to the Zenn API with the provided query parameters.
  async def fetch_articles(query: Article) -> dict: return await request(URLResource.ARTICLES, query.to_query_param())
• src/mcp_server_zenn/server.py:77-140 (schema)

  Pydantic model for 'article' tool input schema, including field definitions, argument parsing (from_arguments), query param building (to_query_param), and Tool schema definition (tool()).
  class Article(BaseModel): """Fetch articles from Zenn.dev""" model_config = ConfigDict( validate_assignment=True, frozen=True, extra="forbid", ) username: Optional[str] = Field(default=None, description="Username of the article author") topicname: Optional[str] = Field(default=None, description="Topic name of the article") order: Optional[Order] = Field( default=Order.LATEST, description=f"Order of the articles. Choose from {Order.LATEST.value} or {Order.OLDEST.value}", ) page: Optional[int] = Field(default=1, description="Page number of the articles. Default: 1") count: Optional[int] = Field(default=48, description="Number of articles per page. Default: 48") @staticmethod def from_arguments(arguments: dict) -> "Article": return Article( username=arguments.get("username"), topicname=arguments.get("topicname"), order=Order.from_str(arguments.get("order", Order.LATEST.value)), page=arguments.get("page", 1), count=arguments.get("count", 48), ) def to_query_param(self) -> dict: param = {} if self.username: param["username"] = self.username.lower() if self.topicname: param["topicname"] = self.topicname.lower() if self.order: param["order"] = self.order.value if self.page: param["page"] = self.page if self.count: param["count"] = self.count return param @staticmethod def tool() -> Tool: return Tool( name=ZennTool.ARTICLE.value, description="Fetch articles from Zenn.dev", inputSchema={ "type": "object", "properties": { "username": {"type": "string", "description": Article.model_fields["username"].description}, "topicname": {"type": "string", "description": Article.model_fields["topicname"].description}, "order": { "type": "string", "description": Article.model_fields["order"].description, "enum": [Order.LATEST.value, Order.OLDEST.value], }, "page": {"type": "integer", "description": Article.model_fields["page"].description}, "count": {"type": "integer", "description": Article.model_fields["count"].description}, }, "required": [], }, )
• src/mcp_server_zenn/server.py:243-246 (registration)

  Registers the 'article' tool with the MCP server by including it in the list of available tools.
  @server.list_tools() async def list_tools() -> list[Tool]: return [Article.tool(), Book.tool()]
• src/mcp_server_zenn/server.py:248-268 (handler)

  MCP server call_tool handler that dispatches calls to the 'article' tool (when name == 'article') to the specific handle_articles function and returns the JSON result as TextContent.
  @server.call_tool() async def call_tool( name: str, arguments: dict, ) -> Sequence[TextContent | ImageContent | EmbeddedResource]: try: logger.debug(f"Calling tool: {name} with arguments: {arguments}") match name: case ZennTool.ARTICLE.value: result = await handle_articles(arguments) case ZennTool.BOOK.value: result = await handle_books(arguments) case _: raise ValueError(f"Unknown tool: {name}") return [TextContent(type="text", text=json.dumps(result, indent=2, ensure_ascii=False))] except Exception as e: logger.error(f"Error processing {APP_NAME} query: {str(e)}") raise ValueError(f"Error processing {APP_NAME} query: {str(e)}")