MCP TabNews Integration
The MCP TabNews Integration server connects to the TabNews API, enabling comprehensive content management and analytics operations:
Check Status: Verify TabNews API availability
Get Contents: Retrieve content lists with pagination and sorting options (relevant, new, old)
Get Contents by User: Fetch all contents posted by a specific user with pagination and sorting
Get Content: Retrieve detailed content including body text using username and slug
Get Comments: Fetch comments associated with specific content
Get Analytics: Access daily analytics for user creation, root content (posts), and child content (comments) published
Get RSS Feed: Retrieve the TabNews RSS feed
Enables fetching the RSS feed from TabNews via the getRssFeedTool
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP TabNews Integration show me the latest posts from TabNews"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP TabNews Integration
A Model Context Protocol (MCP) integration for TabNews.
This MCP server is also available on Smithery for direct integration.
Available Tools
checkStatusTool: Check the status of the TabNews API.getContentsTool: Get contents from TabNews.getContentsByUserTool: Get contents from TabNews by user.getContentTool: Get a content with body from TabNews by user and slug.getContentChildrenTool: Get comments from TabNews by content.getAnalyticsUserCreatedTool: Get the analytics of a user created contents from TabNews.getAnalyticsRootContentPublishedTool: Get the analytics of a root content published from TabNews.getAnalyticsChildContentPublishedTool: Get the analytics of a child content published from TabNews.getRssFeedTool: Get the RSS feed from TabNews.
Integration with AI Tools
Related MCP server: MCP Boilerplate
Inspect MCP Server Capabilities
You can inspect this MCP server's capabilities using Smithery:
npx -y @smithery/cli@latest inspect @renant/mcp-tabnewsThis will show you all available tools, their parameters, and how to use them.
Setup
Manual Installation
Make sure you're using Node.js v23+
node -v
#v23.11.0Clone this repository:
git clone https://github.com/renant/mcp-tabnews.git
cd mcp-tabnewsRestore dependencies:
npm ciIntegration with AI Tools
Cursor Setup
Open Cursor Settings
Navigate to MCP section
Click "Add new MCP server"
Configure the server:
Name = mcp-tabnews Type = command Command = node ABSOLUTE_PATH_TO_PROJECT/src/index.tsor if you prefer executing it from Smithery
Name = mcp-tabnews Type = command Command = npm exec -- @smithery/cli@latest run @renant/mcp-tabnews
or configure directly from the Cursor's global MCP file located in ~/.cursor/mcp.json and add the following:
{
"mcpServers": {
"mcp-tabnews": {
"command": "node",
"args": ["ABSOLUTE_PATH_TO_PROJECT/src/index.ts"]
}
}
}or if you prefer executing it from Smithery
{
"mcpServers": {
"mcp-tabnews": {
"command": "npm",
"args": [
"exec",
"--",
"@smithery/cli@latest",
"run",
"@renant/mcp-tabnews"
]
}
}
}Make sure Cursor chat is in Agent mode by selecting "Agent" in the lower left side dropdown
Go to the chat an ask any question about TabNews
Claude Desktop Setup
Installing via Smithery
To install TabNews for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @renant/mcp-tabnews --client claudeDevelopment
Features
Built with Model Context Protocol (MCP)
Type-safe with TypeScript and Zod schema validation
Native TypeScript support in Node.js without transpilation
Standard I/O transport for easy integration
Structured error handling
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Author
License
This project is licensed under the MIT License - see the LICENSE file for details.
Available Tools
9 toolsget analytics child content publishedB
To get how many comments were made (per day) in tabnews
Inputs: no named parameters.
get analytics root content publishedB
To get how many posts were made (per day) in tabnews
Inputs: no named parameters.
get analytics user createdB
To get how many users were created (per day) in tabnews
Inputs: no named parameters.
get commentsC
get comments from a content on tabnews api
Inputs: username (required), slug (required).
get contentC
get content from tabnews api
Inputs: username (required), slug (required).
get contentsC
get contents from tabnews api
Inputs: page, per_page, strategy.
get contents by userC
get contents by user from tabnews api
Inputs: username (required), page, per_page, strategy.
get rss feedB
To get the rss feed from tabnews
Inputs: no named parameters.
get statusC
get status from tabnews api
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
The tools have some overlap that could cause confusion, particularly between 'get content', 'get contents', and 'get contents by user', as their purposes are similar but not clearly distinct. However, the analytics tools and others like 'get rss feed' and 'get status' are well-separated, reducing overall ambiguity.
The naming is inconsistent, mixing descriptive phrases like 'get analytics child content published' with simpler forms like 'get content' and 'get status'. There is no uniform pattern, with variations in verb usage and structure, making it harder to predict tool names.
With 9 tools, the count is well-scoped for a TabNews integration, covering analytics, content retrieval, and system status without being overwhelming. Each tool appears to serve a specific purpose, making the set manageable and appropriate.
The toolset focuses heavily on read operations (get analytics, get content, get status) but lacks obvious write or update capabilities like creating or modifying content or comments. This creates notable gaps for a full integration, though core retrieval functions are covered.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Managed cloud RSS and Atom feed reader with a remote Model Context Protocol (MCP) endpoint. Zero server setup required — enables AI agents like Claude to instantly subscribe to feeds, search full-text articles, extract readable content, and access curated AI editions ("Your Newspaper") over secure streamable HTTP.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI agents to query Erick Wendel's talks, blog posts, and videos across different platforms using natural language.423 npm386MIT
- AlicenseNot gradedqualityDmaintenanceA server that implements the Model Context Protocol, providing a standardized way to connect AI models to different data sources and tools.10 npm12MIT
- AlicenseAqualityDmaintenanceA server that enables AI assistants to access, analyze, and understand HackerNews content through standardized Model Context Protocol interfaces, providing tools for searching posts, analyzing users, and tracking trending topics.58MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI assistants to securely fetch and extract readable text content from web pages through a standardized interface.1MIT